changelog date [ci skip]

README: document the minimum Go version

.codecov.yml

@@ -0,0 +1,26 @@
+
+#
+# This codecov.yml is the default configuration for
+# all repositories on Codecov. You may adjust the settings
+# below in your own codecov.yml in your repository.
+#
+coverage:
+  precision: 2
+  round: down
+  range: 70...100
+
+  status:
+    # Learn more at https://codecov.io/docs#yaml_default_commit_status
+    project: 
+      default:
+        threshold: 1% # allow this much decrease on project
+    changes: false
+
+comment:
+  layout: "header, diff"
+  behavior: default  # update if exists else create new
+
+ignore:
+  - "docs"
+  - "*.md"
+  - "*.rst"

.editorconfig

@@ -0,0 +1,16 @@
+# top-most EditorConfig file
+root = true
+
+# Unix-style newlines with a newline ending every file
+[*]
+charset = utf-8
+end_of_line = lf
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.{sh,Makefile}]
+indent_style = tab
+
+[*.proto]
+indent_style = space
+indent_size = 2

.github/CODEOWNERS

@@ -0,0 +1,4 @@
+# CODEOWNERS: https://help.github.com/articles/about-codeowners/
+
+# Everything goes through Bucky and Anton. For now.
+*       @ebuchman @melekes

.github/ISSUE_TEMPLATE

@@ -0,0 +1,41 @@
+<!-- Thanks for filing an issue! Before hitting the button, please answer these questions.-->
+
+**Is this a BUG REPORT or FEATURE REQUEST?** (choose one):
+
+<!--
+If this is a BUG REPORT, please:
+  - Fill in as much of the template below as you can.
+
+If this is a FEATURE REQUEST, please:
+  - Describe *in detail* the feature/behavior/change you'd like to see.
+
+In both cases, be ready for followup questions, and please respond in a timely
+manner. We might ask you to provide additional logs and data (tendermint & app)
+in a case of bug.
+-->
+
+**Tendermint version** (use `tendermint version` or `git rev-parse --verify HEAD` if installed from source):
+
+
+**ABCI app** (name for built-in, URL for self-written if it's publicly available):
+
+
+**Merkleeyes version** (use `git rev-parse --verify HEAD`, skip if you don't use it):
+
+
+**Environment**:
+- **OS** (e.g. from /etc/os-release):
+- **Install tools**:
+- **Others**:
+
+
+**What happened**:
+
+
+**What you expected to happen**:
+
+
+**How to reproduce it** (as minimally and precisely as possible):
+
+
+**Anything else do we need to know**:

.gitignore

@@ -10,3 +10,13 @@ rpc/test/.tendermint
 remote_dump
 .revision
 vendor
+.vagrant
+test/p2p/data/
+test/logs
+.glide
+coverage.txt
+docs/_build
+docs/tools
+
+scripts/wal2json/wal2json
+scripts/cutWALUntil/cutWALUntil

CHANGELOG.md

@@ -0,0 +1,572 @@
+# Changelog
+
+## Roadmap
+
+BREAKING CHANGES:
+- Better support for injecting randomness
+- Upgrade consensus for more real-time use of evidence
+
+FEATURES:
+- Peer reputation management
+- Use the chain as its own CA for nodes and validators
+- Tooling to run multiple blockchains/apps, possibly in a single process
+- State syncing (without transaction replay)
+- Add authentication and rate-limitting to the RPC
+
+IMPROVEMENTS:
+- Improve subtleties around mempool caching and logic
+- Consensus optimizations:
+	- cache block parts for faster agreement after round changes
+	- propagate block parts rarest first
+- Better testing of the consensus state machine (ie. use a DSL)
+- Auto compiled serialization/deserialization code instead of go-wire reflection
+
+BUG FIXES:
+- Graceful handling/recovery for apps that have non-determinism or fail to halt
+- Graceful handling/recovery for violations of safety, or liveness
+
+## 0.15.0 (December 29, 2017)
+
+BREAKING CHANGES:
+- [p2p] enable the Peer Exchange reactor by default
+- [types] add Timestamp field to Proposal/Vote
+- [types] add new fields to Header: TotalTxs, ConsensusParamsHash, LastResultsHash, EvidenceHash
+- [types] add Evidence to Block
+- [types] simplify ValidateBasic
+- [state] updates to support changes to the header
+- [state] Enforce <1/3 of validator set can change at a time
+
+FEATURES:
+- [state] Send indices of absent validators and addresses of byzantine validators in BeginBlock
+- [state] Historical ConsensusParams and ABCIResponses
+- [docs] Specification for the base Tendermint data structures.
+- [evidence] New evidence reactor for gossiping and managing evidence
+- [rpc] `/block_results?height=X` returns the DeliverTx results for a given height.
+
+IMPROVEMENTS:
+- [consensus] Better handling of corrupt WAL file
+
+BUG FIXES:
+- [lite] fix race
+- [state] validate block.Header.ValidatorsHash
+- [p2p] allow seed addresses to be prefixed with eg. `tcp://`
+- [p2p] use consistent key to refer to peers so we dont try to connect to existing peers
+- [cmd] fix `tendermint init` to ignore files that are there and generate files that aren't.
+
+## 0.14.0 (December 11, 2017)
+
+BREAKING CHANGES:
+- consensus/wal: removed separator
+- rpc/client: changed Subscribe/Unsubscribe/UnsubscribeAll funcs signatures to be identical to event bus.
+
+FEATURES:
+- new `tendermint lite` command (and `lite/proxy` pkg) for running a light-client RPC proxy.
+    NOTE it is currently insecure and its APIs are not yet covered by semver
+
+IMPROVEMENTS:
+- rpc/client: can act as event bus subscriber (See https://github.com/tendermint/tendermint/issues/945).
+- p2p: use exponential backoff from seconds to hours when attempting to reconnect to persistent peer
+- config: moniker defaults to the machine's hostname instead of "anonymous"
+
+BUG FIXES:
+- p2p: no longer exit if one of the seed addresses is incorrect
+
+## 0.13.0 (December 6, 2017)
+
+BREAKING CHANGES:
+- abci: update to v0.8 using gogo/protobuf; includes tx tags, vote info in RequestBeginBlock, data.Bytes everywhere, use int64, etc.
+- types: block heights are now `int64` everywhere
+- types & node: EventSwitch and EventCache have been replaced by EventBus and EventBuffer; event types have been overhauled
+- node: EventSwitch methods now refer to EventBus
+- rpc/lib/types: RPCResponse is no longer a pointer; WSRPCConnection interface has been modified
+- rpc/client: WaitForOneEvent takes an EventsClient instead of types.EventSwitch
+- rpc/client: Add/RemoveListenerForEvent are now Subscribe/Unsubscribe
+- rpc/core/types: ResultABCIQuery wraps an abci.ResponseQuery
+- rpc: `/subscribe` and `/unsubscribe` take `query` arg instead of `event`
+- rpc: `/status` returns the LatestBlockTime in human readable form instead of in nanoseconds
+- mempool: cached transactions return an error instead of an ABCI response with BadNonce
+
+FEATURES:
+- rpc: new `/unsubscribe_all` WebSocket RPC endpoint
+- rpc: new `/tx_search` endpoint for filtering transactions by more complex queries
+- p2p/trust: new trust metric for tracking peers. See ADR-006
+- config: TxIndexConfig allows to set what DeliverTx tags to index
+
+IMPROVEMENTS:
+- New asynchronous events system using `tmlibs/pubsub`
+- logging: Various small improvements
+- consensus: Graceful shutdown when app crashes
+- tests: Fix various non-deterministic errors
+- p2p: more defensive programming
+
+BUG FIXES:
+- consensus: fix panic where prs.ProposalBlockParts is not initialized
+- p2p: fix panic on bad channel
+
+## 0.12.1 (November 27, 2017)
+
+BUG FIXES:
+- upgrade tmlibs dependency to enable Windows builds for Tendermint
+
+## 0.12.0 (October 27, 2017)
+
+BREAKING CHANGES:
+ - rpc/client: websocket ResultsCh and ErrorsCh unified in ResponsesCh.
+ - rpc/client: ABCIQuery no longer takes `prove`
+ - state: remove GenesisDoc from state.
+ - consensus: new binary WAL format provides efficiency and uses checksums to detect corruption
+    - use scripts/wal2json to convert to json for debugging
+
+FEATURES:
+ - new `certifiers` pkg contains the tendermint light-client library (name subject to change)!
+ - rpc: `/genesis` includes the `app_options` .
+ - rpc: `/abci_query` takes an additional `height` parameter to support historical queries.
+ - rpc/client: new ABCIQueryWithOptions supports options like `trusted` (set false to get a proof) and `height` to query a historical height.
+
+IMPROVEMENTS:
+ - rpc: `/genesis` result includes `app_options`
+ - rpc/lib/client: add jitter to reconnects.
+ - rpc/lib/types: `RPCError` satisfies the `error` interface.
+
+BUG FIXES:
+ - rpc/client: fix ws deadlock after stopping
+ - blockchain: fix panic on AddBlock when peer is nil
+ - mempool: fix sending on TxsAvailable when a tx has been invalidated
+ - consensus: dont run WAL catchup if we fast synced
+
+## 0.11.1 (October 10, 2017)
+
+IMPROVEMENTS:
+ - blockchain/reactor: respondWithNoResponseMessage for missing height
+
+BUG FIXES:
+ - rpc: fixed client WebSocket timeout
+ - rpc: client now resubscribes on reconnection
+ - rpc: fix panics on missing params
+ - rpc: fix `/dump_consensus_state` to have normal json output (NOTE: technically breaking, but worth a bug fix label)
+ - types: fixed out of range error in VoteSet.addVote
+ - consensus: fix wal autofile via https://github.com/tendermint/tmlibs/blob/master/CHANGELOG.md#032-october-2-2017
+
+## 0.11.0 (September 22, 2017)
+
+BREAKING:
+ - genesis file: validator `amount` is now `power`
+ - abci: Info, BeginBlock, InitChain all take structs
+ - rpc: various changes to match JSONRPC spec (http://www.jsonrpc.org/specification), including breaking ones:
+    - requests that previously returned HTTP code 4XX now return 200 with an error code in the JSONRPC.
+    - `rpctypes.RPCResponse` uses new `RPCError` type instead of `string`.
+
+ - cmd: if there is no genesis, exit immediately instead of waiting around for one to show.
+ - types: `Signer.Sign` returns an error.
+ - state: every validator set change is persisted to disk, which required some changes to the `State` structure.
+ - p2p: new `p2p.Peer` interface used for all reactor methods (instead of `*p2p.Peer` struct).
+
+FEATURES:
+ - rpc: `/validators?height=X` allows querying of validators at previous heights.
+ - rpc: Leaving the `height` param empty for `/block`, `/validators`, and `/commit` will return the value for the latest height.
+
+IMPROVEMENTS:
+ - docs: Moved all docs from the website and tools repo in, converted to `.rst`, and cleaned up for presentation on `tendermint.readthedocs.io`
+
+BUG FIXES:
+ - fix WAL openning issue on Windows
+
+## 0.10.4 (September 5, 2017)
+
+IMPROVEMENTS:
+- docs: Added Slate docs to each rpc function (see rpc/core)
+- docs: Ported all website docs to Read The Docs
+- config: expose some p2p params to tweak performance: RecvRate, SendRate, and MaxMsgPacketPayloadSize
+- rpc: Upgrade the websocket client and server, including improved auto reconnect, and proper ping/pong
+
+BUG FIXES:
+- consensus: fix panic on getVoteBitArray
+- consensus: hang instead of panicking on byzantine consensus failures
+- cmd: dont load config for version command
+
+## 0.10.3 (August 10, 2017)
+
+FEATURES:
+- control over empty block production:
+  - new flag, `--consensus.create_empty_blocks`; when set to false, blocks are only created when there are txs or when the AppHash changes.
+  - new config option, `consensus.create_empty_blocks_interval`; an empty block is created after this many seconds.
+  - in normal operation, `create_empty_blocks = true` and `create_empty_blocks_interval = 0`, so blocks are being created all the time (as in all previous versions of tendermint). The number of empty blocks can be reduced by increasing `create_empty_blocks_interval` or by setting `create_empty_blocks = false`.
+  - new `TxsAvailable()` method added to Mempool that returns a channel which fires when txs are available.
+  - new heartbeat message added to consensus reactor to notify peers that a node is waiting for txs before entering propose step.
+- rpc: Add `syncing` field to response returned by `/status`. Is `true` while in fast-sync mode.
+
+IMPROVEMENTS:
+- various improvements to documentation and code comments
+
+BUG FIXES:
+- mempool: pass height into constructor so it doesn't always start at 0
+
+## 0.10.2 (July 10, 2017)
+
+FEATURES:
+- Enable lower latency block commits by adding consensus reactor sleep durations and p2p flush throttle timeout to the config
+
+IMPROVEMENTS:
+- More detailed logging in the consensus reactor and state machine
+- More in-code documentation for many exposed functions, especially in consensus/reactor.go and p2p/switch.go
+- Improved readability for some function definitions and code blocks with long lines
+
+## 0.10.1 (June 28, 2017)
+
+FEATURES:
+- Use `--trace` to get stack traces for logged errors
+- types: GenesisDoc.ValidatorHash returns the hash of the genesis validator set
+- types: GenesisDocFromFile parses a GenesiDoc from a JSON file
+
+IMPROVEMENTS:
+- Add a Code of Conduct
+- Variety of improvements as suggested by `megacheck` tool
+- rpc: deduplicate tests between rpc/client and rpc/tests
+- rpc: addresses without a protocol prefix default to `tcp://`. `http://` is also accepted as an alias for `tcp://`
+- cmd: commands are more easily reuseable from other tools
+- DOCKER: automate build/push
+
+BUG FIXES:
+- Fix log statements using keys with spaces (logger does not currently support spaces)
+- rpc: set logger on websocket connection
+- rpc: fix ws connection stability by setting write deadline on pings
+
+## 0.10.0 (June 2, 2017)
+
+Includes major updates to configuration, logging, and json serialization.
+Also includes the Grand Repo-Merge of 2017.
+
+BREAKING CHANGES:
+
+- Config and Flags:
+  - The `config` map is replaced with a [`Config` struct](https://github.com/tendermint/tendermint/blob/master/config/config.go#L11),
+containing substructs: `BaseConfig`, `P2PConfig`, `MempoolConfig`, `ConsensusConfig`, `RPCConfig`
+  - This affects the following flags:
+    - `--seeds` is now `--p2p.seeds`
+    - `--node_laddr` is now `--p2p.laddr`
+    - `--pex` is now `--p2p.pex`
+    - `--skip_upnp` is now `--p2p.skip_upnp`
+    - `--rpc_laddr` is now `--rpc.laddr`
+    - `--grpc_laddr` is now `--rpc.grpc_laddr`
+  - Any configuration option now within a substract must come under that heading in the `config.toml`, for instance:
+    ```
+    [p2p]
+    laddr="tcp://1.2.3.4:46656"
+
+    [consensus]
+    timeout_propose=1000
+    ```
+  - Use viper and `DefaultConfig() / TestConfig()` functions to handle defaults, and remove `config/tendermint` and `config/tendermint_test`
+  - Change some function and method signatures to
+  - Change some [function and method signatures](https://gist.github.com/ebuchman/640d5fc6c2605f73497992fe107ebe0b) accomodate new config
+
+- Logger
+  - Replace static `log15` logger with a simple interface, and provide a new implementation using `go-kit`.
+See our new [logging library](https://github.com/tendermint/tmlibs/log) and [blog post](https://tendermint.com/blog/abstracting-the-logger-interface-in-go) for more details
+  - Levels `warn` and `notice` are removed (you may need to change them in your `config.toml`!)
+  - Change some [function and method signatures](https://gist.github.com/ebuchman/640d5fc6c2605f73497992fe107ebe0b) to accept a logger
+
+- JSON serialization:
+  - Replace `[TypeByte, Xxx]` with `{"type": "some-type", "data": Xxx}` in RPC and all `.json` files by using `go-wire/data`. For instance, a public key is now:
+    ```
+    "pub_key": {
+      "type": "ed25519",
+      "data": "83DDF8775937A4A12A2704269E2729FCFCD491B933C4B0A7FFE37FE41D7760D0"
+    }
+    ```
+  - Remove type information about RPC responses, so `[TypeByte, {"jsonrpc": "2.0", ... }]` is now just `{"jsonrpc": "2.0", ... }`
+  - Change `[]byte` to `data.Bytes` in all serialized types (for hex encoding)
+  - Lowercase the JSON tags in `ValidatorSet` fields
+  - Introduce `EventDataInner` for serializing events
+
+- Other:
+  - Send InitChain message in handshake if `appBlockHeight == 0`
+  - Do not include the `Accum` field when computing the validator hash. This makes the ValidatorSetHash unique for a given validator set, rather than changing with every block (as the Accum changes)
+  - Unsafe RPC calls are not enabled by default. This includes `/dial_seeds`, and all calls prefixed with `unsafe`. Use the `--rpc.unsafe` flag to enable.
+
+
+FEATURES:
+
+- Per-module log levels. For instance, the new default is `state:info,*:error`, which means the `state` package logs at `info` level, and everything else logs at `error` level
+- Log if a node is validator or not in every consensus round
+- Use ldflags to set git hash as part of the version
+- Ignore `address` and `pub_key` fields in `priv_validator.json` and overwrite them with the values derrived from the `priv_key`
+
+IMPROVEMENTS:
+
+- Merge `tendermint/go-p2p -> tendermint/tendermint/p2p` and `tendermint/go-rpc -> tendermint/tendermint/rpc/lib`
+- Update paths for grand repo merge:
+  - `go-common -> tmlibs/common`
+  - `go-data -> go-wire/data`
+  - All other `go-` libs, except `go-crypto` and `go-wire`, are merged under `tmlibs`
+- No global loggers (loggers are passed into constructors, or preferably set with a SetLogger method)
+- Return HTTP status codes with errors for RPC responses
+- Limit `/blockchain_info` call to return a maximum of 20 blocks
+- Use `.Wrap()` and `.Unwrap()` instead of eg. `PubKeyS` for `go-crypto` types
+- RPC JSON responses use pretty printing (via `json.MarshalIndent`)
+- Color code different instances of the consensus for tests
+- Isolate viper to `cmd/tendermint/commands` and do not read config from file for tests
+
+
+## 0.9.2 (April 26, 2017)
+
+BUG FIXES:
+
+- Fix bug in `ResetPrivValidator` where we were using the global config and log (causing external consumers, eg. basecoin, to fail).
+
+## 0.9.1 (April 21, 2017)
+
+FEATURES:
+
+- Transaction indexing - txs are indexed by their hash using a simple key-value store; easily extended to more advanced indexers
+- New `/tx?hash=X` endpoint to query for transactions and their DeliverTx result by hash. Optionally returns a proof of the tx's inclusion in the block
+- `tendermint testnet` command initializes files for a testnet
+
+IMPROVEMENTS:
+
+- CLI now uses Cobra framework
+- TMROOT is now TMHOME (TMROOT will stop working in 0.10.0)
+- `/broadcast_tx_XXX` also returns the Hash (can be used to query for the tx)
+- `/broadcast_tx_commit` also returns the height the block was committed in
+- ABCIResponses struct persisted to disk before calling Commit; makes handshake replay much cleaner
+- WAL uses #ENDHEIGHT instead of #HEIGHT (#HEIGHT will stop working in 0.10.0)
+- Peers included via `--seeds`, under `seeds` in the config, or in `/dial_seeds` are now persistent, and will be reconnected to if the connection breaks
+
+BUG FIXES:
+
+- Fix bug in fast-sync where we stop syncing after a peer is removed, even if they're re-added later
+- Fix handshake replay to handle validator set changes and results of DeliverTx when we crash after app.Commit but before state.Save()
+
+## 0.9.0 (March 6, 2017)
+
+BREAKING CHANGES:
+
+- Update ABCI to v0.4.0, where Query is now `Query(RequestQuery) ResponseQuery`, enabling precise proofs at particular heights:
+
+```
+message RequestQuery{
+	bytes data = 1;
+	string path = 2;
+	uint64 height = 3;
+	bool prove = 4;
+}
+
+message ResponseQuery{
+	CodeType          code        = 1;
+	int64             index       = 2;
+	bytes             key         = 3;
+	bytes             value       = 4;
+	bytes             proof       = 5;
+	uint64            height      = 6;
+	string            log         = 7;
+}
+```
+
+
+- `BlockMeta` data type unifies its Hash and PartSetHash under a `BlockID`:
+
+```
+type BlockMeta struct {
+	BlockID BlockID `json:"block_id"` // the block hash and partsethash
+	Header  *Header `json:"header"`   // The block's Header
+}
+```
+
+- `ValidatorSet.Proposer` is exposed as a field and persisted with the `State`. Use `GetProposer()` to initialize or update after validator-set changes.
+
+- `tendermint gen_validator` command output is now pure JSON
+
+FEATURES:
+
+- New RPC endpoint `/commit?height=X` returns header and commit for block at height `X`
+- Client API for each endpoint, including mocks for testing
+
+IMPROVEMENTS:
+
+- `Node` is now a `BaseService`
+- Simplified starting Tendermint in-process from another application
+- Better organized Makefile
+- Scripts for auto-building binaries across platforms
+- Docker image improved, slimmed down (using Alpine), and changed from tendermint/tmbase to tendermint/tendermint
+- New repo files: `CONTRIBUTING.md`, Github `ISSUE_TEMPLATE`, `CHANGELOG.md`
+- Improvements on CircleCI for managing build/test artifacts
+- Handshake replay is doen through the consensus package, possibly using a mockApp
+- Graceful shutdown of RPC listeners
+- Tests for the PEX reactor and DialSeeds
+
+BUG FIXES:
+
+- Check peer.Send for failure before updating PeerState in consensus
+- Fix panic in `/dial_seeds` with invalid addresses
+- Fix proposer selection logic in ValidatorSet by taking the address into account in the `accumComparable`
+- Fix inconcistencies with `ValidatorSet.Proposer` across restarts by persisting it in the `State`
+
+
+## 0.8.0 (January 13, 2017)
+
+BREAKING CHANGES:
+
+- New data type `BlockID` to represent blocks:
+
+```
+type BlockID struct {
+	Hash        []byte        `json:"hash"`
+	PartsHeader PartSetHeader `json:"parts"`
+}
+```
+
+- `Vote` data type now includes validator address and index:
+
+```
+type Vote struct {
+	ValidatorAddress []byte           `json:"validator_address"`
+	ValidatorIndex   int              `json:"validator_index"`
+	Height           int              `json:"height"`
+	Round            int              `json:"round"`
+	Type             byte             `json:"type"`
+	BlockID          BlockID          `json:"block_id"` // zero if vote is nil.
+	Signature        crypto.Signature `json:"signature"`
+}
+```
+
+- Update TMSP to v0.3.0, where it is now called ABCI and AppendTx is DeliverTx
+- Hex strings in the RPC are now "0x" prefixed
+
+
+FEATURES:
+
+- New message type on the ConsensusReactor, `Maj23Msg`, for peers to alert others they've seen a Maj23,
+in order to track and handle conflicting votes intelligently to prevent Byzantine faults from causing halts:
+
+```
+type VoteSetMaj23Message struct {
+	Height  int
+	Round   int
+	Type    byte
+	BlockID types.BlockID
+}
+```
+
+- Configurable block part set size
+- Validator set changes
+- Optionally skip TimeoutCommit if we have all the votes
+- Handshake between Tendermint and App on startup to sync latest state and ensure consistent recovery from crashes
+- GRPC server for BroadcastTx endpoint
+
+IMPROVEMENTS:
+
+- Less verbose logging
+- Better test coverage (37% -> 49%)
+- Canonical SignBytes for signable types
+- Write-Ahead Log for Mempool and Consensus via tmlibs/autofile
+- Better in-process testing for the consensus reactor and byzantine faults
+- Better crash/restart testing for individual nodes at preset failure points, and of networks at arbitrary points
+- Better abstraction over timeout mechanics
+
+BUG FIXES:
+
+- Fix memory leak in mempool peer
+- Fix panic on POLRound=-1
+- Actually set the CommitTime
+- Actually send BeginBlock message
+- Fix a liveness issues caused by Byzantine proposals/votes. Uses the new `Maj23Msg`.
+
+
+## 0.7.4 (December 14, 2016)
+
+FEATURES:
+
+- Enable the Peer Exchange reactor with the `--pex` flag for more resilient gossip network (feature still in development, beware dragons)
+
+IMPROVEMENTS:
+
+- Remove restrictions on RPC endpoint `/dial_seeds` to enable manual network configuration
+
+## 0.7.3 (October 20, 2016)
+
+IMPROVEMENTS:
+
+- Type safe FireEvent
+- More WAL/replay tests
+- Cleanup some docs
+
+BUG FIXES:
+
+- Fix deadlock in mempool for synchronous apps
+- Replay handles non-empty blocks
+- Fix race condition in HeightVoteSet
+
+## 0.7.2 (September 11, 2016)
+
+BUG FIXES:
+
+- Set mustConnect=false so tendermint will retry connecting to the app
+
+## 0.7.1 (September 10, 2016)
+
+FEATURES:
+
+- New TMSP connection for Query/Info
+- New RPC endpoints:
+	- `tmsp_query`
+	- `tmsp_info`
+- Allow application to filter peers through Query (off by default)
+
+IMPROVEMENTS:
+
+- TMSP connection type enforced at compile time
+- All listen/client urls use a "tcp://" or "unix://" prefix
+
+BUG FIXES:
+
+- Save LastSignature/LastSignBytes to `priv_validator.json` for recovery
+- Fix event unsubscribe
+- Fix fastsync/blockchain reactor
+
+## 0.7.0 (August 7, 2016)
+
+BREAKING CHANGES:
+
+- Strict SemVer starting now!
+- Update to ABCI v0.2.0
+- Validation types now called Commit
+- NewBlock event only returns the block header
+
+
+FEATURES:
+
+- TMSP and RPC support TCP and UNIX sockets
+- Addition config options including block size and consensus parameters
+- New WAL mode `cswal_light`; logs only the validator's own votes
+- New RPC endpoints:
+	- for starting/stopping profilers, and for updating config
+	- `/broadcast_tx_commit`, returns when tx is included in a block, else an error
+	- `/unsafe_flush_mempool`, empties the mempool
+
+
+IMPROVEMENTS:
+
+- Various optimizations
+- Remove bad or invalidated transactions from the mempool cache (allows later duplicates)
+- More elaborate testing using CircleCI including benchmarking throughput on 4 digitalocean droplets
+
+BUG FIXES:
+
+- Various fixes to WAL and replay logic
+- Various race conditions
+
+## PreHistory
+
+Strict versioning only began with the release of v0.7.0, in late summer 2016.
+The project itself began in early summer 2014 and was workable decentralized cryptocurrency software by the end of that year.
+Through the course of 2015, in collaboration with Eris Industries (now Monax Indsutries),
+many additional features were integrated, including an implementation from scratch of the Ethereum Virtual Machine.
+That implementation now forms the heart of [Burrow](https://github.com/hyperledger/burrow).
+In the later half of 2015, the consensus algorithm was upgraded with a more asynchronous design and a more deterministic and robust implementation.
+
+By late 2015, frustration with the difficulty of forking a large monolithic stack to create alternative cryptocurrency designs led to the
+invention of the Application Blockchain Interface (ABCI), then called the Tendermint Socket Protocol (TMSP).
+The Ethereum Virtual Machine and various other transaction features were removed, and Tendermint was whittled down to a core consensus engine
+driving an application running in another process.
+The ABCI interface and implementation were iterated on and improved over the course of 2016,
+until versioned history kicked in with v0.7.0.

CODE_OF_CONDUCT.md

@@ -0,0 +1,56 @@
+# The Tendermint Code of Conduct
+This code of conduct applies to all projects run by the Tendermint/COSMOS team and hence to tendermint.
+
+
+----
+
+
+# Conduct
+## Contact: adrian@tendermint.com
+
+* We are committed to providing a friendly, safe and welcoming environment for all, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, religion, nationality, or other similar characteristic.
+
+* On Slack, please avoid using overtly sexual nicknames or other nicknames that might detract from a friendly, safe and welcoming environment for all.
+
+* Please be kind and courteous. There’s no need to be mean or rude.
+
+* Respect that people have differences of opinion and that every design or implementation choice carries a trade-off and numerous costs. There is seldom a right answer.
+
+* Please keep unstructured critique to a minimum. If you have solid ideas you want to experiment with, make a fork and see how it works.
+
+* We will exclude you from interaction if you insult, demean or harass anyone. That is not welcome behaviour. We interpret the term “harassment” as including the definition in the [Citizen Code of Conduct](http://citizencodeofconduct.org/); if you have any lack of clarity about what might be included in that concept, please read their definition. In particular, we don’t tolerate behavior that excludes people in socially marginalized groups.
+
+* Private harassment is also unacceptable. No matter who you are, if you feel you have been or are being harassed or made uncomfortable by a community member, please contact one of the channel admins or the person mentioned above immediately. Whether you’re a regular contributor or a newcomer, we care about making this community a safe place for you and we’ve got your back.
+
+* Likewise any spamming, trolling, flaming, baiting or other attention-stealing behaviour is not welcome.
+
+
+----
+
+
+# Moderation
+These are the policies for upholding our community’s standards of conduct. If you feel that a thread needs moderation, please contact the above mentioned person.
+
+1. Remarks that violate the Tendermint/COSMOS standards of conduct, including hateful, hurtful, oppressive, or exclusionary remarks, are not allowed. (Cursing is allowed, but never targeting another user, and never in a hateful manner.)
+
+2. Remarks that moderators find inappropriate, whether listed in the code of conduct or not, are also not allowed.
+
+3. Moderators will first respond to such remarks with a warning.
+
+4. If the warning is unheeded, the user will be “kicked,” i.e., kicked out of the communication channel to cool off.
+
+5. If the user comes back and continues to make trouble, they will be banned, i.e., indefinitely excluded.
+
+6. Moderators may choose at their discretion to un-ban the user if it was a first offense and they offer the offended party a genuine apology.
+
+7. If a moderator bans someone and you think it was unjustified, please take it up with that moderator, or with a different moderator, in private. Complaints about bans in-channel are not allowed.
+
+8. Moderators are held to a higher standard than other community members. If a moderator creates an inappropriate situation, they should expect less leeway than others.
+
+In the Tendermint/COSMOS community we strive to go the extra step to look out for each other. Don’t just aim to be technically unimpeachable, try to be your best self. In particular, avoid flirting with offensive or sensitive issues, particularly if they’re off-topic; this all too often leads to unnecessary fights, hurt feelings, and damaged trust; worse, it can drive people away from the community entirely.
+
+And if someone takes issue with something you said or did, resist the urge to be defensive. Just stop doing what it was they complained about and apologize. Even if you feel you were misinterpreted or unfairly accused, chances are good there was something you could’ve communicated better — remember that it’s your responsibility to make your fellow Cosmonauts comfortable. Everyone wants to get along and we are all here first and foremost because we want to talk about cool technology. You will find that people will be eager to assume good intent and forgive as long as you earn their trust.
+
+The enforcement policies listed above apply to all official Tendermint/COSMOS venues.For other projects adopting the Tendermint/COSMOS Code of Conduct, please contact the maintainers of those projects for enforcement. If you wish to use this code of conduct for your own project, consider explicitly mentioning your moderation policy or making a copy with your own moderation policy so as to avoid confusion.
+
+*Adapted from the [Node.js Policy on Trolling](http://blog.izs.me/post/30036893703/policy-on-trolling), the [Contributor Covenant v1.3.0](http://contributor-covenant.org/version/1/3/0/) and the [Rust Code of Conduct](https://www.rust-lang.org/en-US/conduct.html).

CONTRIBUTING.md

@@ -0,0 +1,100 @@
+# Contributing
+
+Thank you for considering making contributions to Tendermint and related repositories! Start by taking a look at the [coding repo](https://github.com/tendermint/coding) for overall information on repository workflow and standards.
+
+Please follow standard github best practices: fork the repo, branch from the tip of develop, make some commits, and submit a pull request to develop. See the [open issues](https://github.com/tendermint/tendermint/issues) for things we need help with!
+
+Please make sure to use `gofmt` before every commit - the easiest way to do this is have your editor run it for you upon saving a file.
+
+## Forking
+
+Please note that Go requires code to live under absolute paths, which complicates forking.
+While my fork lives at `https://github.com/ebuchman/tendermint`,
+the code should never exist at  `$GOPATH/src/github.com/ebuchman/tendermint`.
+Instead, we use `git remote` to add the fork as a new remote for the original repo,
+`$GOPATH/src/github.com/tendermint/tendermint `, and do all the work there.
+
+For instance, to create a fork and work on a branch of it, I would:
+
+  * Create the fork on github, using the fork button.
+  * Go to the original repo checked out locally (ie. `$GOPATH/src/github.com/tendermint/tendermint`)
+  * `git remote rename origin upstream`
+  * `git remote add origin git@github.com:ebuchman/basecoin.git`
+
+Now `origin` refers to my fork and `upstream` refers to the tendermint version.
+So I can `git push -u origin master` to update my fork, and make pull requests to tendermint from there.
+Of course, replace `ebuchman` with your git handle.
+
+To pull in updates from the origin repo, run
+
+    * `git fetch upstream`
+    * `git rebase upstream/master` (or whatever branch you want)
+
+Please don't make Pull Requests to `master`.
+
+## Dependencies
+
+We use [glide](https://github.com/masterminds/glide) to manage dependencies.
+That said, the master branch of every Tendermint repository should just build with `go get`, which means they should be kept up-to-date with their dependencies so we can get away with telling people they can just `go get` our software.
+Since some dependencies are not under our control, a third party may break our build, in which case we can fall back on `glide install`. Even for dependencies under our control, glide helps us keeps multiple repos in sync as they evolve. Anything with an executable, such as apps, tools, and the core, should use glide.
+
+Run `bash scripts/glide/status.sh` to get a list of vendored dependencies that may not be up-to-date.
+
+## Vagrant
+
+If you are a [Vagrant](https://www.vagrantup.com/) user, all you have to do to get started hacking Tendermint is:
+
+```
+vagrant up
+vagrant ssh
+cd ~/go/src/github.com/tendermint/tendermint
+make test
+```
+
+## Testing
+
+All repos should be hooked up to circle.
+If they have `.go` files in the root directory, they will be automatically tested by circle using `go test -v -race ./...`. If not, they will need a `circle.yml`. Ideally, every repo has a `Makefile` that defines `make test` and includes its continuous integration status using a badge in the `README.md`.
+
+## Branching Model and Release
+
+User-facing repos should adhere to the branching model: http://nvie.com/posts/a-successful-git-branching-model/.
+That is, these repos should be well versioned, and any merge to master requires a version bump and tagged release.
+
+Libraries need not follow the model strictly, but would be wise to,
+especially `go-p2p` and `go-rpc`, as their versions are referenced in tendermint core.
+
+### Development Procedure:
+- the latest state of development is on `develop`
+- `develop` must never fail `make test`
+- no --force onto `develop` (except when reverting a broken commit, which should seldom happen)
+- create a development branch either on github.com/tendermint/tendermint, or your fork (using `git add origin`)
+- before submitting a pull request, begin `git rebase` on top of `develop`
+
+### Pull Merge Procedure:
+- ensure pull branch is rebased on develop
+- run `make test` to ensure that all tests pass
+- merge pull request
+- the `unstable` branch may be used to aggregate pull merges before testing once
+- push master may request that pull requests be rebased on top of `unstable`
+
+### Release Procedure:
+- start on `develop`
+- run integration tests (see `test_integrations` in Makefile)
+- prepare changelog/release issue
+- bump versions
+- push to release-vX.X.X to run the extended integration tests on the CI
+- merge to master
+- merge master back to develop
+
+### Hotfix Procedure:
+- start on `master`
+- checkout a new branch named hotfix-vX.X.X
+- make the required changes
+  - these changes should be small and an absolute necessity
+  - add a note to CHANGELOG.md
+- bumb versions
+- push to hotfix-vX.X.X to run the extended integration tests on the CI
+- merge hotfix-vX.X.X to master
+- merge hotfix-vX.X.X to develop
+- delete the hotfix-vX.X.X branch

DOCKER/Dockerfile

@@ -1,54 +1,45 @@
-# Pull base image.
-FROM golang:1.6
+FROM alpine:3.6
 
-ENV USER tmuser
-ENV DATA_ROOT /data/tendermint
+# This is the release of tendermint to pull in.
+ENV TM_VERSION 0.13.0
+ENV TM_SHA256SUM 36d773d4c2890addc61cc87a72c1e9c21c89516921b0defb0edfebde719b4b85
+
+# Tendermint will be looking for genesis file in /tendermint (unless you change
+# `genesis_file` in config.toml). You can put your config.toml and private
+# validator file into /tendermint.
+#
+# The /tendermint/data dir is used by tendermint to store state.
+ENV DATA_ROOT /tendermint
+ENV TMHOME $DATA_ROOT
 
 # Set user right away for determinism
-RUN groupadd -r $USER \
-  && useradd -r -s /bin/false -g $USER $USER
-
-# Create home directory for USER
-# Needed for nodejs/nom
-RUN mkdir -p /home/$USER \
-  && chown -R $USER:$USER /home/$USER
+RUN addgroup tmuser && \
+    adduser -S -G tmuser tmuser
 
 # Create directory for persistence and give our user ownership
-RUN mkdir -p $DATA_ROOT \
-  && chown -R $USER:$USER $DATA_ROOT
+RUN mkdir -p $DATA_ROOT && \
+    chown -R tmuser:tmuser $DATA_ROOT
 
-# Set the env variables to non-interactive
-ENV DEBIAN_FRONTEND noninteractive
-ENV DEBIAN_PRIORITY critical
-ENV DEBCONF_NOWARNINGS yes
-ENV TERM linux
-RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
+# jq and curl used for extracting `pub_key` from private validator while
+# deploying tendermint with Kubernetes. It is nice to have bash so the users
+# could execute bash commands.
+RUN apk add --no-cache bash curl jq
 
-# Grab deps (git)
-RUN apt-get update && \
-  apt-get install -y --no-install-recommends \
-    git && \
-  rm -rf /var/lib/apt/lists/*
+RUN apk add --no-cache openssl && \
+    wget https://s3-us-west-2.amazonaws.com/tendermint/binaries/tendermint/v${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
+    echo "${TM_SHA256SUM}  tendermint_${TM_VERSION}_linux_amd64.zip" | sha256sum -c && \
+    unzip -d /bin tendermint_${TM_VERSION}_linux_amd64.zip && \
+    apk del openssl && \
+    rm -f tendermint_${TM_VERSION}_linux_amd64.zip
 
-# Grab deps (node)
-RUN curl -sL https://deb.nodesource.com/setup_5.x | bash -
-RUN apt-get update && \
-  apt-get install -y --no-install-recommends \
-    nodejs && \
-  rm -rf /var/lib/apt/lists/*
-
-# Copy run.sh
-COPY ./run.sh $DATA_ROOT/run.sh
-RUN chmod +x $DATA_ROOT/run.sh
-
-# Persist data, set user
-WORKDIR $DATA_ROOT
+# Expose the data directory as a volume since there's mutable state in there
 VOLUME $DATA_ROOT
-USER $USER
-ENV TMROOT $DATA_ROOT
 
+# p2p port
 EXPOSE 46656
+# rpc port
 EXPOSE 46657
 
-# Run tendermint
-CMD ["./run.sh"]
+ENTRYPOINT ["tendermint"]
+
+CMD ["node", "--moniker=`hostname`"]

DOCKER/Dockerfile.develop

@@ -0,0 +1,35 @@
+FROM alpine:3.6
+
+ENV DATA_ROOT /tendermint
+ENV TMHOME $DATA_ROOT
+
+RUN addgroup tmuser && \
+    adduser -S -G tmuser tmuser
+
+RUN mkdir -p $DATA_ROOT && \
+    chown -R tmuser:tmuser $DATA_ROOT
+
+RUN apk add --no-cache bash curl jq
+
+ENV GOPATH /go
+ENV PATH "$PATH:/go/bin"
+RUN mkdir -p /go/src/github.com/tendermint/tendermint && \
+    apk add --no-cache go build-base git && \
+    cd /go/src/github.com/tendermint/tendermint && \
+    git clone https://github.com/tendermint/tendermint . && \
+    git checkout develop && \
+    make get_vendor_deps && \
+    make install && \
+    glide cc && \
+    cd - && \
+    rm -rf /go/src/github.com/tendermint/tendermint && \
+    apk del go build-base git
+
+VOLUME $DATA_ROOT
+
+EXPOSE 46656
+EXPOSE 46657
+
+ENTRYPOINT ["tendermint"]
+
+CMD ["node", "--moniker=`hostname`", "--proxy_app=dummy"]

DOCKER/Makefile

@@ -0,0 +1,13 @@
+build:
+	@sh -c "'$(CURDIR)/build.sh'"
+
+push:
+	@sh -c "'$(CURDIR)/push.sh'"
+
+build_develop:
+	docker build -t "tendermint/tendermint:develop" -f Dockerfile.develop .
+
+push_develop:
+	docker push "tendermint/tendermint:develop"
+
+.PHONY: build build_develop push push_develop

DOCKER/README.md

@@ -1,13 +1,59 @@
-# Build and run a docker image and container
+# Supported tags and respective `Dockerfile` links
+
+- `0.13.0`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/a28b3fff49dce2fb31f90abb2fc693834e0029c2/DOCKER/Dockerfile)
+- `0.12.1` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/457c688346b565e90735431619ca3ca597ef9007/DOCKER/Dockerfile)
+- `0.12.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/70d8afa6e952e24c573ece345560a5971bf2cc0e/DOCKER/Dockerfile)
+- `0.11.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/9177cc1f64ca88a4a0243c5d1773d10fba67e201/DOCKER/Dockerfile)
+- `0.10.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/e5342f4054ab784b2cd6150e14f01053d7c8deb2/DOCKER/Dockerfile)
+- `0.9.1`, `0.9`, [(Dockerfile)](https://github.com/tendermint/tendermint/blob/809e0e8c5933604ba8b2d096803ada7c5ec4dfd3/DOCKER/Dockerfile)
+- `0.9.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/d474baeeea6c22b289e7402449572f7c89ee21da/DOCKER/Dockerfile)
+- `0.8.0`, `0.8` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/bf64dd21fdb193e54d8addaaaa2ecf7ac371de8c/DOCKER/Dockerfile)
+- `develop` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/master/DOCKER/Dockerfile.develop)
+
+`develop` tag points to the [develop](https://github.com/tendermint/tendermint/tree/develop) branch.
+
+# Quick reference
+
+* **Where to get help:**
+  https://tendermint.com/community
+
+* **Where to file issues:**
+  https://github.com/tendermint/tendermint/issues
+
+* **Supported Docker versions:**
+  [the latest release](https://github.com/moby/moby/releases) (down to 1.6 on a best-effort basis)
+
+# Tendermint
+
+Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine, written in any programming language, and securely replicates it on many machines.
+
+For more background, see the [introduction](https://tendermint.readthedocs.io/en/master/introduction.html).
+
+To get started developing applications, see the [application developers guide](https://tendermint.readthedocs.io/en/master/getting-started.html).
+
+# How to use this image
+
+## Start one instance of the Tendermint core with the `dummy` app
+
+A very simple example of a built-in app and Tendermint core in one container.
 
 ```
-# Build base Docker image
-# Make sure ./run.sh exists.
-docker build -t tendermint/tmbase -f Dockerfile .
-
-# Log into dockerhub
-docker login
-
-# Push latest build to dockerhub
-docker push tendermint/tmbase
+docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint init
+docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint node --proxy_app=dummy
 ```
+
+## mintnet-kubernetes
+
+If you want to see many containers talking to each other, consider using [mintnet-kubernetes](https://github.com/tendermint/tools/tree/master/mintnet-kubernetes), which is a tool for running Tendermint-based applications on a Kubernetes cluster.
+
+# License
+
+View [license information](https://raw.githubusercontent.com/tendermint/tendermint/master/LICENSE) for the software contained in this image.
+
+# User Feedback
+
+## Contributing
+
+You are invited to contribute new features, fixes, or updates, large or small; we are always thrilled to receive pull requests, and do our best to process them as fast as we can.
+
+Before you start to code, we recommend discussing your plans through a [GitHub](https://github.com/tendermint/tendermint/issues) issue, especially for more ambitious contributions. This gives other contributors a chance to point you in the right direction, give you feedback on your design, and help you find out if someone else is working on the same thing.

DOCKER/build.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -e
+
+# Get the tag from the version, or try to figure it out.
+if [ -z "$TAG" ]; then
+	TAG=$(awk -F\" '/Version =/ { print $2; exit }' < ../version/version.go)
+fi
+if [ -z "$TAG" ]; then
+		echo "Please specify a tag."
+		exit 1
+fi
+
+TAG_NO_PATCH=${TAG%.*}
+
+read -p "==> Build 3 docker images with the following tags (latest, $TAG, $TAG_NO_PATCH)? y/n" -n 1 -r
+echo
+if [[ $REPLY =~ ^[Yy]$ ]]
+then
+		docker build -t "tendermint/tendermint" -t "tendermint/tendermint:$TAG" -t "tendermint/tendermint:$TAG_NO_PATCH" .
+fi

DOCKER/push.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+set -e
+
+# Get the tag from the version, or try to figure it out.
+if [ -z "$TAG" ]; then
+	TAG=$(awk -F\" '/Version =/ { print $2; exit }' < ../version/version.go)
+fi
+if [ -z "$TAG" ]; then
+		echo "Please specify a tag."
+		exit 1
+fi
+
+TAG_NO_PATCH=${TAG%.*}
+
+read -p "==> Push 3 docker images with the following tags (latest, $TAG, $TAG_NO_PATCH)? y/n" -n 1 -r
+echo
+if [[ $REPLY =~ ^[Yy]$ ]]
+then
+	docker push "tendermint/tendermint:latest"
+	docker push "tendermint/tendermint:$TAG"
+	docker push "tendermint/tendermint:$TAG_NO_PATCH"
+fi

DOCKER/run.sh

@@ -1,10 +0,0 @@
-#! /bin/bash
-
-mkdir -p $GOPATH/src/$TMREPO
-cd $GOPATH/src/$TMREPO
-git clone https://$TMREPO.git .
-git fetch
-git reset --hard $TMHEAD
-go get -d $TMREPO/cmd/tendermint
-make
-tendermint node --seeds="$TMSEEDS" --moniker="$TMNAME"

INSTALL/FORK_TESTNET.md

@@ -1,21 +0,0 @@
-1. Fork github.com/tendermint/tendermint.
-2. Run "make", it should install the daemon, which we named "tendermint".
-3. Run "tendermint gen_account".  Save the address, pub_key bytes, and priv_key bytes.
-   This is your developer key for controlling the cloud nodes.
-4. Also run "tendermint gen_validator" 5 times, once for each cloud node.  Save the output.
-5. Create a directory ~/.debora/ and copy cmd/debora/default.cfg into ~/.debora/default.cfg
-   Copy the priv_key bytes from step 4 into ~/.debora/default.cfg where it says so.
-   Change the list of hosts in ~/.debora/default.cfg with your own set of 5 cloud nodes.
-6. Replace cmd/barak/seed's pubkey with the pub_key bytes from step 3.
-7. Update config/tendermint/config.go's genesis with validator pubkeys from step 4.
-   Give each of your nodes the same amount of voting power.
-   Set up the accounts however you want.
-8. On each cloud node, follow the instructions here: https://github.com/tendermint/tendermint/tree/master/INSTALL
-   Create tmuser, install go, and also install 'barak'.
-   Then, run `barak -config="cmd/barak/seed"`.
-   You don't need to start the node at this time.
-9. Now you can run "debora list" on your development machine and post commands to each cloud node.
-10. Run scripts/unsafe_upgrade_barak.sh to test that barak is running.
-    The old barak you started on step 8 should now have quit.
-    A new instance of barak should be running.  Check with `ps -ef | grep "barak"`
-11. Run scripts/unsafe_restart_net.sh start your new testnet.

INSTALL/README.md

@@ -1,30 +0,0 @@
-NOTE: Only Ubuntu 14.04 64bit is supported at this time.
-
-### Server setup / create `tmuser`
-
-Secure the server, install dependencies, and create a new user `tmuser`
-
-    curl -L https://raw.githubusercontent.com/tendermint/tendermint/master/INSTALL/install_env.sh > install_env.sh
-    source install_env.sh
-    cd /home/tmuser
-
-### Install Go as `tmuser`
-
-Don't use `apt-get install golang`, it's still on an old version.
-
-    curl -L https://raw.githubusercontent.com/tendermint/tendermint/master/INSTALL/install_golang.sh > install_golang.sh
-    source install_golang.sh
-
-### Run Barak
-
-WARNING: THIS STEP WILL GIVE CONTROL OF THE CURRENT USER TO THE DEV TEAM.
-
-    go get -u github.com/tendermint/tendermint/cmd/barak
-    nohup barak -config="$GOPATH/src/github.com/tendermint/tendermint/cmd/barak/seed" &
-
-### Install/Update MintDB
-
-    go get -u github.com/tendermint/tendermint/cmd/tendermint
-    mkdir -p ~/.tendermint
-    cp $GOPATH/src/github.com/tendermint/tendermint/config/tendermint/genesis.json ~/.tendermint/
-    tendermint node --seeds="goldenalchemist.chaintest.net:46656"

INSTALL/install_env.sh

@@ -1,63 +0,0 @@
-#!/bin/bash
-# Run this as root user
-# This part is for hardening the server and setting up a user account
-
-if [ `whoami` != "root" ];
-then
-  echo "You must run this script as root"
-  exit 1
-fi
-
-USER="tmuser"
-OPEN_PORTS=(46656 46657 46658 46659 46660 46661 46662 46663 46664 46665 46666 46667 46668 46669 46670 46671)
-SSH_PORT=22
-WHITELIST=()
-
-# update and upgrade
-apt-get update -y
-apt-get upgrade -y
-
-# fail2ban for monitoring logins
-apt-get install -y fail2ban
-
-# set up the network time daemon
-apt-get install -y ntp
-
-# install dependencies
-apt-get install -y make screen gcc git mercurial libc6-dev pkg-config libgmp-dev
-
-# set up firewall
-echo "ENABLE FIREWALL ..."
-set -x
-# white list ssh access 
-for ip in "${WHITELIST[@]}"; do
-	ufw allow from $ip to any port $SSH_PORT
-done
-if [ ${#WHITELIST[@]} -eq 0 ]; then
-	ufw allow $SSH_PORT
-fi
-# open ports
-for port in "${OPEN_PORTS[@]}"; do
-	ufw allow $port
-done
-# apply
-ufw --force enable
-set +x
-# set up firewall END
-
-# watch the logs and have them emailed to me
-# apt-get install -y logwatch
-# echo "/usr/sbin/logwatch --output mail --mailto $ADMIN_EMAIL --detail high" >> /etc/cron.daily/00logwatch
-
-# set up user account
-echo "CREATE USER $USER ..."
-useradd $USER -d /home/$USER
-# This user should not have root access.
-# usermod -aG sudo $USER
-mkdir /home/$USER
-cp /etc/skel/.bashrc .
-cp /etc/skel/.profile .
-chown -R $USER:$USER /home/$USER
-
-echo "Done setting env.  Switching to $USER..."
-su $USER

INSTALL/install_golang.sh

@@ -1,29 +0,0 @@
-#!/bin/bash
-# Run this as tmuser user
-# This part is for installing go
-
-if [ `whoami` == "root" ];
-then
-  echo "You should not run this script as root"
-  exit 1
-fi
-
-USER=`whoami`
-PWD=`pwd`
-
-# get dependencies
-# sudo apt-get install -y make screen gcc git mercurial libc6-dev pkg-config libgmp-dev
-
-# install golang
-cd /home/$USER
-mkdir gocode
-wget https://storage.googleapis.com/golang/go1.4.2.src.tar.gz
-tar -xzvf go*.tar.gz
-cd go/src
-./make.bash
-mkdir -p /home/$USER/go/src
-echo 'export GOROOT=/home/$USER/go' >> /home/$USER/.bashrc
-echo 'export GOPATH=/home/$USER/gocode' >> /home/$USER/.bashrc
-echo 'export PATH=$PATH:$GOROOT/bin:$GOPATH/bin' >> /home/$USER/.bashrc
-source /home/$USER/.bashrc
-cd $PWD

Makefile

@@ -1,58 +1,132 @@
-.PHONY: get_deps build all list_deps install
+GOTOOLS = \
+	github.com/mitchellh/gox \
+	github.com/Masterminds/glide \
+	github.com/tcnksm/ghr \
+	gopkg.in/alecthomas/gometalinter.v2
+GOTOOLS_CHECK = gox glide ghr gometalinter.v2
+PACKAGES=$(shell go list ./... | grep -v '/vendor/')
+BUILD_TAGS?=tendermint
+TMHOME = $${TMHOME:-$$HOME/.tendermint}
+BUILD_FLAGS = -ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse --short HEAD`"
 
-all: get_deps install test
+all: check build test install metalinter
 
-TMROOT = $${TMROOT:-$$HOME/.tendermint}
-define NEWLINE
+check: check_tools get_vendor_deps
 
 
-endef
-NOVENDOR = go list github.com/tendermint/tendermint/... | grep -v /vendor/
+########################################
+### Build
 
-install: get_deps
-	go install github.com/tendermint/tendermint/cmd/tendermint
+build:
+	go build $(BUILD_FLAGS) -o build/tendermint ./cmd/tendermint/
 
-build: 
-	go build -o build/tendermint github.com/tendermint/tendermint/cmd/tendermint
+build_race:
+	go build -race $(BUILD_FLAGS) -o build/tendermint ./cmd/tendermint
 
-build_race: 
-	go build -race -o build/tendermint github.com/tendermint/tendermint/cmd/tendermint
+# dist builds binaries for all platforms and packages them for distribution
+dist:
+	@BUILD_TAGS='$(BUILD_TAGS)' sh -c "'$(CURDIR)/scripts/dist.sh'"
 
-test: build
-	go test `${NOVENDOR}`
-	
-test_race: build
-	go test -race `${NOVENDOR}`
+install:
+	go install $(BUILD_FLAGS) ./cmd/tendermint
 
-test_integrations: 
-	bash ./test/test.sh
 
-test100: build
-	for i in {1..100}; do make test; done
+########################################
+### Tools & dependencies
 
-draw_deps:
-	# requires brew install graphviz
-	go get github.com/hirokidaichi/goviz
-	goviz -i github.com/tendermint/tendermint/cmd/tendermint | dot -Tpng -o huge.png
+check_tools:
+	@# https://stackoverflow.com/a/25668869
+	@echo "Found tools: $(foreach tool,$(GOTOOLS_CHECK),\
+        $(if $(shell which $(tool)),$(tool),$(error "No $(tool) in PATH")))"
 
-list_deps:
-	go list -f '{{join .Deps "\n"}}' github.com/tendermint/tendermint/... | \
-		grep -v /vendor/ | sort | uniq | \
-	  xargs go list -f '{{if not .Standard}}{{.ImportPath}}{{end}}'
+get_tools:
+	@echo "--> Installing tools"
+	go get -u -v $(GOTOOLS)
+	@gometalinter.v2 --install
 
-get_deps:
-	go get -d `${NOVENDOR}`
-	go list -f '{{join .TestImports "\n"}}' github.com/tendermint/tendermint/... | \
-		grep -v /vendor/ | sort | uniq | \
-		xargs go get
+update_tools:
+	@echo "--> Updating tools"
+	@go get -u $(GOTOOLS)
 
 get_vendor_deps:
-	go get github.com/Masterminds/glide
-	glide install
+	@rm -rf vendor/
+	@echo "--> Running glide install"
+	@glide install
 
-update_deps:
-	go get -d -u github.com/tendermint/tendermint/...
+draw_deps:
+	@# requires brew install graphviz or apt-get install graphviz
+	go get github.com/RobotsAndPencils/goviz
+	@goviz -i github.com/tendermint/tendermint/cmd/tendermint -d 3 | dot -Tpng -o dependency-graph.png
 
-revision:
-	-echo `git rev-parse --verify HEAD` > $(TMROOT)/revision
-	-echo `git rev-parse --verify HEAD` >> $(TMROOT)/revision_history
+
+########################################
+### Testing
+
+test:
+	@echo "--> Running go test"
+	@go test $(PACKAGES)
+
+test_race:
+	@echo "--> Running go test --race"
+	@go test -v -race $(PACKAGES)
+
+test_integrations:
+	@bash ./test/test.sh
+
+test_release:
+	@go test -tags release $(PACKAGES)
+
+test100:
+	@for i in {1..100}; do make test; done
+
+vagrant_test:
+	vagrant up
+	vagrant ssh -c 'make install'
+	vagrant ssh -c 'make test_race'
+	vagrant ssh -c 'make test_integrations'
+
+
+########################################
+### Formatting, linting, and vetting
+
+fmt:
+	@go fmt ./...
+
+metalinter:
+	@echo "--> Running linter"
+	gometalinter.v2 --vendor --deadline=600s --disable-all  \
+		--enable=deadcode \
+		--enable=gosimple \
+	 	--enable=misspell \
+		--enable=safesql \
+		./...
+		#--enable=gas \
+		#--enable=maligned \
+		#--enable=dupl \
+		#--enable=errcheck \
+		#--enable=goconst \
+		#--enable=gocyclo \
+		#--enable=goimports \
+		#--enable=golint \ <== comments on anything exported
+		#--enable=gotype \
+	 	#--enable=ineffassign \
+	   	#--enable=interfacer \
+	   	#--enable=megacheck \
+	   	#--enable=staticcheck \
+	   	#--enable=structcheck \
+	   	#--enable=unconvert \
+	   	#--enable=unparam \
+		#--enable=unused \
+	   	#--enable=varcheck \
+		#--enable=vet \
+		#--enable=vetshadow \
+
+metalinter_all:
+	@echo "--> Running linter (all)"
+	gometalinter.v2 --vendor --deadline=600s --enable-all --disable=lll ./...
+
+
+# To avoid unintended conflicts with file names, always add to .PHONY
+# unless there is a reason not to.
+# https://www.gnu.org/software/make/manual/html_node/Phony-Targets.html
+.PHONY: check build build_race dist install check_tools get_tools update_tools get_vendor_deps draw_deps test test_race test_integrations test_release test100 vagrant_test fmt metalinter metalinter_all

README.md

@@ -1,43 +1,112 @@
 # Tendermint
-Simple, Secure, Scalable Blockchain Platform
 
-[![CircleCI](https://circleci.com/gh/tendermint/tendermint.svg?style=svg)](https://circleci.com/gh/tendermint/tendermint)
-[![codecov](https://codecov.io/gh/tendermint/tendermint/branch/develop/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint)
+[Byzantine-Fault Tolerant](https://en.wikipedia.org/wiki/Byzantine_fault_tolerance)
+[State Machine Replication](https://en.wikipedia.org/wiki/State_machine_replication).
+Or [Blockchain](https://en.wikipedia.org/wiki/Blockchain_(database)) for short.
 
-_NOTE: This is yet pre-alpha non-production-quality software._
+[![version](https://img.shields.io/github/tag/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/releases/latest)
+[![API Reference](
+https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667
+)](https://godoc.org/github.com/tendermint/tendermint)
+[![Go version](https://img.shields.io/badge/go-1.9.2-blue.svg)](https://github.com/moovweb/gvm)
+[![Rocket.Chat](https://demo.rocket.chat/images/join-chat.svg)](https://cosmos.rocket.chat/)
+[![license](https://img.shields.io/github/license/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/blob/master/LICENSE)
+[![](https://tokei.rs/b1/github/tendermint/tendermint?category=lines)](https://github.com/tendermint/tendermint)
 
-Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine, written in any programming language,
-and replicates it on many machines.
-See the [application developers guide](https://github.com/tendermint/tendermint/wiki/Application-Developers) to get started.
 
-## Contributing
+Branch    | Tests | Coverage
+----------|-------|----------
+master    | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/master.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/master) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/master/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint)
+develop   | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/develop.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/develop) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/develop/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint)
 
-Yay open source! Please see our [contributing guidelines](https://github.com/tendermint/tendermint/wiki/Contributing).
+_NOTE: This is alpha software. Please contact us if you intend to run it in production._
+
+Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine - written in any programming language -
+and securely replicates it on many machines.
+
+For more information, from introduction to install to application development, [Read The Docs](https://tendermint.readthedocs.io/en/master/).
+
+## Minimum requirements
+
+Requirement|Notes
+---|---
+Go version | Go1.9 or higher
+
+## Install
+
+To download pre-built binaries, see our [downloads page](https://tendermint.com/downloads).
+
+To install from source, you should be able to:
+
+`go get -u github.com/tendermint/tendermint/cmd/tendermint`
+
+For more details (or if it fails), [read the docs](https://tendermint.readthedocs.io/en/master/install.html).
 
 ## Resources
 
 ### Tendermint Core
 
-- [Introduction](https://github.com/tendermint/tendermint/wiki/Introduction)
-- [Validators](https://github.com/tendermint/tendermint/wiki/Validators)
-- [Byzantine Consensus Algorithm](https://github.com/tendermint/tendermint/wiki/Byzantine-Consensus-Algorithm)
-- [Block Structure](https://github.com/tendermint/tendermint/wiki/Block-Structure)
-- [RPC](https://github.com/tendermint/tendermint/wiki/RPC)
-- [Genesis](https://github.com/tendermint/tendermint/wiki/Genesis)
-- [Configuration](https://github.com/tendermint/tendermint/wiki/Configuration)
-- [Light Client Protocol](https://github.com/tendermint/tendermint/wiki/Light-Client-Protocol)
-- [Roadmap for V2](https://github.com/tendermint/tendermint/wiki/Roadmap-for-V2)
+All resources involving the use of, building application on, or developing for, tendermint, can be found at [Read The Docs](https://tendermint.readthedocs.io/en/master/). Additional information about some - and eventually all - of the sub-projects below, can be found at Read The Docs.
 
 ### Sub-projects
 
-* [TMSP](http://github.com/tendermint/tmsp)
-* [Mintnet](http://github.com/tendermint/mintnet)
-* [Go-Wire](http://github.com/tendermint/go-wire)
-* [Go-P2P](http://github.com/tendermint/go-p2p)
-* [Go-Merkle](http://github.com/tendermint/go-merkle)
+* [ABCI](http://github.com/tendermint/abci), the Application Blockchain Interface
+* [Go-Wire](http://github.com/tendermint/go-wire), a deterministic serialization library
+* [Go-Crypto](http://github.com/tendermint/go-crypto), an elliptic curve cryptography library
+* [TmLibs](http://github.com/tendermint/tmlibs), an assortment of Go libraries used internally
+* [IAVL](http://github.com/tendermint/iavl), Merkleized IAVL+ Tree implementation
 
-## Install
+### Tools
+* [Deployment, Benchmarking, and Monitoring](http://tendermint.readthedocs.io/projects/tools/en/develop/index.html#tendermint-tools)
 
-`go get -u github.com/tendermint/tendermint/cmd/tendermint`
+### Applications
 
-For more details, see the [install guide](https://github.com/tendermint/tendermint/wiki/Installation).
+* [Ethermint](http://github.com/tendermint/ethermint); Ethereum on Tendermint
+* [Cosmos SDK](http://github.com/cosmos/cosmos-sdk); a cryptocurrency application framework
+* [Many more](https://tendermint.readthedocs.io/en/master/ecosystem.html#abci-applications)
+
+### More
+
+* [Master's Thesis on Tendermint](https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9769)
+* [Original Whitepaper](https://tendermint.com/static/docs/tendermint.pdf)
+* [Tendermint Blog](https://blog.cosmos.network/tendermint/home)
+* [Cosmos Blog](https://blog.cosmos.network)
+
+## Contributing
+
+Yay open source! Please see our [contributing guidelines](CONTRIBUTING.md).
+
+## Versioning
+
+### SemVer
+
+Tendermint uses [SemVer](http://semver.org/) to determine when and how the version changes.
+According to SemVer, anything in the public API can change at any time before version 1.0.0
+
+To provide some stability to Tendermint users in these 0.X.X days, the MINOR version is used
+to signal breaking changes across a subset of the total public API. This subset includes all
+interfaces exposed to other processes (cli, rpc, p2p, etc.), as well as parts of the following packages:
+
+- types
+- rpc/client
+- config
+- node
+
+Exported objects in these packages that are not covered by the versioning scheme
+are explicitly marked by `// UNSTABLE` in their go doc comment and may change at any time.
+Functions, types, and values in any other package may also change at any time.
+
+### Upgrades
+
+In an effort to avoid accumulating technical debt prior to 1.0.0,
+we do not guarantee that breaking changes (ie. bumps in the MINOR version)
+will work with existing tendermint blockchains. In these cases you will
+have to start a new blockchain, or write something custom to get the old
+data into the new chain.
+
+However, any bump in the PATCH version should be compatible with existing histories
+(if not please open an [issue](https://github.com/tendermint/tendermint/issues)).
+
+## Code of Conduct
+
+Please read, understand and adhere to our [code of conduct](CODE_OF_CONDUCT.md).

Vagrantfile

@@ -1,25 +1,49 @@
 # -*- mode: ruby -*-
 # vi: set ft=ruby :
 
-# Vagrantfile API/syntax version. Don't touch unless you know what you're doing!
-VAGRANTFILE_API_VERSION = "2"
+Vagrant.configure("2") do |config|
+  config.vm.box = "ubuntu/xenial64"
 
-Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
-  config.vm.box = "phusion-open-ubuntu-14.04-amd64"
-  config.vm.box_url = "https://oss-binaries.phusionpassenger.com/vagrant/boxes/latest/ubuntu-14.04-amd64-vbox.box"
-  # Or, for Ubuntu 12.04:
-
-  config.vm.provider :vmware_fusion do |f, override|
-    override.vm.box_url = "https://oss-binaries.phusionpassenger.com/vagrant/boxes/latest/ubuntu-14.04-amd64-vmwarefusion.box"
+  config.vm.provider "virtualbox" do |v|
+    v.memory = 4096
+    v.cpus = 2
   end
 
-  if Dir.glob("#{File.dirname(__FILE__)}/.vagrant/machines/default/*/id").empty?
-    # Install Docker
-    pkg_cmd = "wget -q -O - https://get.docker.io/gpg | apt-key add -;" \
-      "echo deb http://get.docker.io/ubuntu docker main > /etc/apt/sources.list.d/docker.list;" \
-      "apt-get update -qq; apt-get install -q -y --force-yes lxc-docker; "
-    # Add vagrant user to the docker group
-    pkg_cmd << "usermod -a -G docker vagrant; "
-    config.vm.provision :shell, :inline => pkg_cmd
-  end
+  config.vm.provision "shell", inline: <<-SHELL
+    # add docker repo
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+    add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu xenial stable"
+
+    # and golang 1.9 support
+    # official repo doesn't have race detection runtime...
+    # add-apt-repository ppa:gophers/archive
+    add-apt-repository ppa:longsleep/golang-backports
+
+    # install base requirements
+    apt-get update
+    apt-get install -y --no-install-recommends wget curl jq \
+        make shellcheck bsdmainutils psmisc
+    apt-get install -y docker-ce golang-1.9-go
+
+    # needed for docker
+    usermod -a -G docker ubuntu
+
+    # use "EOF" not EOF to avoid variable substitution of $PATH
+    cat << "EOF" >> /home/ubuntu/.bash_profile
+export PATH=$PATH:/usr/lib/go-1.9/bin:/home/ubuntu/go/bin
+export GOPATH=/home/ubuntu/go
+export LC_ALL=en_US.UTF-8
+cd go/src/github.com/tendermint/tendermint
+EOF
+
+    mkdir -p /home/ubuntu/go/bin
+    mkdir -p /home/ubuntu/go/src/github.com/tendermint
+    ln -s /vagrant /home/ubuntu/go/src/github.com/tendermint/tendermint
+
+    chown -R ubuntu:ubuntu /home/ubuntu/go
+    chown ubuntu:ubuntu /home/ubuntu/.bash_profile
+
+    # get all deps and tools, ready to install/test
+    su - ubuntu -c 'cd /home/ubuntu/go/src/github.com/tendermint/tendermint && make get_vendor_deps && make tools'
+  SHELL
 end

appveyor.yml

@@ -0,0 +1,13 @@
+version: 1.0.{build}
+configuration: Release
+platform:
+- x64
+- x86
+clone_folder: c:\go\path\src\github.com\tendermint\tendermint
+before_build:
+- cmd: set GOPATH=%GOROOT%\path
+- cmd: set PATH=%GOPATH%\bin;%PATH%
+- cmd: make get_vendor_deps
+build_script:
+- cmd: make test
+test: off

benchmarks/blockchain/.gitignore

@@ -0,0 +1,2 @@
+data
+

benchmarks/blockchain/localsync.sh

@@ -0,0 +1,80 @@
+#!/bin/bash
+
+DATA=$GOPATH/src/github.com/tendermint/tendermint/benchmarks/blockchain/data
+if [ ! -d $DATA ]; then
+  echo "no data found, generating a chain... (this only has to happen once)"
+
+  tendermint init --home $DATA
+  cp $DATA/config.toml $DATA/config2.toml
+  echo "
+  [consensus]
+  timeout_commit = 0
+  " >> $DATA/config.toml
+
+  echo "starting node"
+  tendermint node \
+    --home $DATA \
+    --proxy_app dummy \
+    --p2p.laddr tcp://127.0.0.1:56656 \
+    --rpc.laddr tcp://127.0.0.1:56657 \
+    --log_level error &
+
+  echo "making blocks for 60s"
+  sleep 60
+
+  mv $DATA/config2.toml $DATA/config.toml
+
+  kill %1
+
+  echo "done generating chain."
+fi
+
+# validator node
+HOME1=$TMPDIR$RANDOM$RANDOM
+cp -R $DATA $HOME1
+echo "starting validator node"
+tendermint node \
+  --home $HOME1 \
+  --proxy_app dummy \
+  --p2p.laddr tcp://127.0.0.1:56656 \
+  --rpc.laddr tcp://127.0.0.1:56657 \
+  --log_level error &
+sleep 1
+
+# downloader node
+HOME2=$TMPDIR$RANDOM$RANDOM
+tendermint init --home $HOME2
+cp $HOME1/genesis.json $HOME2
+printf "starting downloader node"
+tendermint node \
+  --home $HOME2 \
+  --proxy_app dummy \
+  --p2p.laddr tcp://127.0.0.1:56666 \
+  --rpc.laddr tcp://127.0.0.1:56667 \
+  --p2p.seeds 127.0.0.1:56656 \
+  --log_level error &
+
+# wait for node to start up so we only count time where we are actually syncing
+sleep 0.5
+while curl localhost:56667/status 2> /dev/null | grep "\"latest_block_height\": 0," > /dev/null
+do
+  printf '.'
+  sleep 0.2
+done
+echo
+
+echo "syncing blockchain for 10s"
+for i in {1..10}
+do
+  sleep 1
+  HEIGHT="$(curl localhost:56667/status 2> /dev/null \
+    | grep 'latest_block_height' \
+    | grep -o ' [0-9]*' \
+    | xargs)"
+  let 'RATE = HEIGHT / i'
+  echo "height: $HEIGHT, blocks/sec: $RATE"
+done
+
+kill %1
+kill %2
+rm -rf $HOME1 $HOME2

benchmarks/codec_test.go

@@ -2,20 +2,22 @@ package benchmarks
 
 import (
 	"testing"
+	"time"
 
 	"github.com/tendermint/go-crypto"
-	"github.com/tendermint/go-p2p"
 	"github.com/tendermint/go-wire"
+
 	proto "github.com/tendermint/tendermint/benchmarks/proto"
+	"github.com/tendermint/tendermint/p2p"
 	ctypes "github.com/tendermint/tendermint/rpc/core/types"
 )
 
 func BenchmarkEncodeStatusWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
+	pubKey := crypto.GenPrivKeyEd25519().PubKey()
 	status := &ctypes.ResultStatus{
 		NodeInfo: &p2p.NodeInfo{
-			PubKey:     pubKey,
+			PubKey:     pubKey.Unwrap().(crypto.PubKeyEd25519),
 			Moniker:    "SOMENAME",
 			Network:    "SOMENAME",
 			RemoteAddr: "SOMEADDR",
@@ -26,7 +28,7 @@ func BenchmarkEncodeStatusWire(b *testing.B) {
 		PubKey:            pubKey,
 		LatestBlockHash:   []byte("SOMEBYTES"),
 		LatestBlockHeight: 123,
-		LatestBlockTime:   1234,
+		LatestBlockTime:   time.Unix(0, 1234),
 	}
 	b.StartTimer()
 
@@ -40,7 +42,7 @@ func BenchmarkEncodeStatusWire(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
+	pubKey := crypto.GenPrivKeyEd25519().PubKey().Unwrap().(crypto.PubKeyEd25519)
 	nodeInfo := &p2p.NodeInfo{
 		PubKey:     pubKey,
 		Moniker:    "SOMENAME",
@@ -61,7 +63,7 @@ func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
+	pubKey := crypto.GenPrivKeyEd25519().PubKey().Unwrap().(crypto.PubKeyEd25519)
 	nodeInfo := &p2p.NodeInfo{
 		PubKey:     pubKey,
 		Moniker:    "SOMENAME",
@@ -83,7 +85,7 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoProto(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
+	pubKey := crypto.GenPrivKeyEd25519().PubKey().Unwrap().(crypto.PubKeyEd25519)
 	pubKey2 := &proto.PubKey{Ed25519: &proto.PubKeyEd25519{Bytes: pubKey[:]}}
 	nodeInfo := &proto.NodeInfo{
 		PubKey:     pubKey2,

benchmarks/map_test.go

@@ -1,8 +1,9 @@
 package benchmarks
 
 import (
-	. "github.com/tendermint/go-common"
 	"testing"
+
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func BenchmarkSomething(b *testing.B) {
@@ -11,11 +12,11 @@ func BenchmarkSomething(b *testing.B) {
 	numChecks := 100000
 	keys := make([]string, numItems)
 	for i := 0; i < numItems; i++ {
-		keys[i] = RandStr(100)
+		keys[i] = cmn.RandStr(100)
 	}
 	txs := make([]string, numChecks)
 	for i := 0; i < numChecks; i++ {
-		txs[i] = RandStr(100)
+		txs[i] = cmn.RandStr(100)
 	}
 	b.StartTimer()
 

benchmarks/os_test.go

@@ -4,7 +4,7 @@ import (
 	"os"
 	"testing"
 
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func BenchmarkFileWrite(b *testing.B) {
@@ -14,16 +14,20 @@ func BenchmarkFileWrite(b *testing.B) {
 	if err != nil {
 		b.Error(err)
 	}
-	testString := RandStr(200) + "\n"
+	testString := cmn.RandStr(200) + "\n"
 	b.StartTimer()
 
 	for i := 0; i < b.N; i++ {
-		file.Write([]byte(testString))
+		_, err := file.Write([]byte(testString))
+		if err != nil {
+			b.Error(err)
+		}
 	}
 
-	file.Close()
-	err = os.Remove("benchmark_file_write.out")
-	if err != nil {
+	if err := file.Close(); err != nil {
+		b.Error(err)
+	}
+	if err := os.Remove("benchmark_file_write.out"); err != nil {
 		b.Error(err)
 	}
 }

benchmarks/proto/test.pb.go

@@ -24,9 +24,6 @@ import bytes "bytes"
 
 import strings "strings"
 import github_com_gogo_protobuf_proto "github.com/gogo/protobuf/proto"
-import sort "sort"
-import strconv "strconv"
-import reflect "reflect"
 
 import io "io"
 
@@ -392,31 +389,6 @@ func (this *PubKeyEd25519) GoString() string {
 	s = append(s, "}")
 	return strings.Join(s, "")
 }
-func valueToGoStringTest(v interface{}, typ string) string {
-	rv := reflect.ValueOf(v)
-	if rv.IsNil() {
-		return "nil"
-	}
-	pv := reflect.Indirect(rv).Interface()
-	return fmt.Sprintf("func(v %v) *%v { return &v } ( %#v )", typ, typ, pv)
-}
-func extensionToGoStringTest(e map[int32]github_com_gogo_protobuf_proto.Extension) string {
-	if e == nil {
-		return "nil"
-	}
-	s := "map[int32]proto.Extension{"
-	keys := make([]int, 0, len(e))
-	for k := range e {
-		keys = append(keys, int(k))
-	}
-	sort.Ints(keys)
-	ss := []string{}
-	for _, k := range keys {
-		ss = append(ss, strconv.Itoa(k)+": "+e[int32(k)].GoString())
-	}
-	s += strings.Join(ss, ",") + "}"
-	return s
-}
 func (m *ResultStatus) Marshal() (data []byte, err error) {
 	size := m.Size()
 	data = make([]byte, size)
@@ -586,24 +558,6 @@ func (m *PubKeyEd25519) MarshalTo(data []byte) (int, error) {
 	return i, nil
 }
 
-func encodeFixed64Test(data []byte, offset int, v uint64) int {
-	data[offset] = uint8(v)
-	data[offset+1] = uint8(v >> 8)
-	data[offset+2] = uint8(v >> 16)
-	data[offset+3] = uint8(v >> 24)
-	data[offset+4] = uint8(v >> 32)
-	data[offset+5] = uint8(v >> 40)
-	data[offset+6] = uint8(v >> 48)
-	data[offset+7] = uint8(v >> 56)
-	return offset + 8
-}
-func encodeFixed32Test(data []byte, offset int, v uint32) int {
-	data[offset] = uint8(v)
-	data[offset+1] = uint8(v >> 8)
-	data[offset+2] = uint8(v >> 16)
-	data[offset+3] = uint8(v >> 24)
-	return offset + 4
-}
 func encodeVarintTest(data []byte, offset int, v uint64) int {
 	for v >= 1<<7 {
 		data[offset] = uint8(v&0x7f | 0x80)
@@ -689,9 +643,6 @@ func sovTest(x uint64) (n int) {
 	}
 	return n
 }
-func sozTest(x uint64) (n int) {
-	return sovTest(uint64((x << 1) ^ uint64((int64(x) >> 63))))
-}
 func (this *ResultStatus) String() string {
 	if this == nil {
 		return "nil"
@@ -742,14 +693,6 @@ func (this *PubKeyEd25519) String() string {
 	}, "")
 	return s
 }
-func valueToStringTest(v interface{}) string {
-	rv := reflect.ValueOf(v)
-	if rv.IsNil() {
-		return "nil"
-	}
-	pv := reflect.Indirect(rv).Interface()
-	return fmt.Sprintf("*%v", pv)
-}
 func (m *ResultStatus) Unmarshal(data []byte) error {
 	var hasFields [1]uint64
 	l := len(data)

benchmarks/simu/counter.go

@@ -1,30 +1,27 @@
 package main
 
 import (
+	"context"
 	"encoding/binary"
-	"time"
-	//"encoding/hex"
 	"fmt"
+	"time"
 
-	"github.com/gorilla/websocket"
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-rpc/client"
-	"github.com/tendermint/go-rpc/types"
-	"github.com/tendermint/go-wire"
-	_ "github.com/tendermint/tendermint/rpc/core/types" // Register RPCResponse > Result types
+	rpcclient "github.com/tendermint/tendermint/rpc/lib/client"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func main() {
-	ws := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
-	_, err := ws.Start()
+	wsc := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
+	err := wsc.Start()
 	if err != nil {
-		Exit(err.Error())
+		cmn.Exit(err.Error())
 	}
+	defer wsc.Stop()
 
 	// Read a bunch of responses
 	go func() {
 		for {
-			_, ok := <-ws.ResultsCh
+			_, ok := <-wsc.ResponsesCh
 			if !ok {
 				break
 			}
@@ -37,19 +34,14 @@ func main() {
 	for i := 0; ; i++ {
 		binary.BigEndian.PutUint64(buf, uint64(i))
 		//txBytes := hex.EncodeToString(buf[:n])
-		request := rpctypes.NewRPCRequest("fakeid", "broadcast_tx", Arr(buf[:8]))
-		reqBytes := wire.JSONBytes(request)
-		//fmt.Println("!!", string(reqBytes))
 		fmt.Print(".")
-		err := ws.WriteMessage(websocket.TextMessage, reqBytes)
+		err = wsc.Call(context.TODO(), "broadcast_tx", map[string]interface{}{"tx": buf[:8]})
 		if err != nil {
-			Exit(err.Error())
+			cmn.Exit(err.Error())
 		}
 		if i%1000 == 0 {
 			fmt.Println(i)
 		}
 		time.Sleep(time.Microsecond * 1000)
 	}
-
-	ws.Stop()
 }

blockchain/log.go

@@ -1,7 +0,0 @@
-package blockchain
-
-import (
-	"github.com/tendermint/go-logger"
-)
-
-var log = logger.New("module", "blockchain")

blockchain/pool.go

@@ -5,16 +5,31 @@ import (
 	"sync"
 	"time"
 
-	flow "github.com/tendermint/flowcontrol"
-	. "github.com/tendermint/go-common"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	flow "github.com/tendermint/tmlibs/flowrate"
+	"github.com/tendermint/tmlibs/log"
 )
 
+/*
+
+eg, L = latency = 0.1s
+	P = num peers = 10
+	FN = num full nodes
+	BS = 1kB block size
+	CB = 1 Mbit/s = 128 kB/s
+	CB/P = 12.8 kB
+	B/S = CB/P/BS = 12.8 blocks/s
+
+	12.8 * 0.1 = 1.28 blocks on conn
+
+*/
+
 const (
-	requestIntervalMS         = 250
-	maxTotalRequesters        = 300
+	requestIntervalMS         = 100
+	maxTotalRequesters        = 1000
 	maxPendingRequests        = maxTotalRequesters
-	maxPendingRequestsPerPeer = 75
+	maxPendingRequestsPerPeer = 50
 	minRecvRate               = 10240 // 10Kb/s
 )
 
@@ -26,59 +41,59 @@ var peerTimeoutSeconds = time.Duration(15) // not const so we can override with
 	in sequence from peers that reported higher heights than ours.
 	Every so often we ask peers what height they're on so we can keep going.
 
-	Requests are continuously made for blocks of heigher heights until
-	the limits. If most of the requests have no available peers, and we
+	Requests are continuously made for blocks of higher heights until
+	the limit is reached. If most of the requests have no available peers, and we
 	are not at peer limits, we can probably switch to consensus reactor
 */
 
 type BlockPool struct {
-	QuitService
+	cmn.BaseService
 	startTime time.Time
 
 	mtx sync.Mutex
 	// block requests
-	requesters map[int]*bpRequester
-	height     int   // the lowest key in requesters.
+	requesters map[int64]*bpRequester
+	height     int64 // the lowest key in requesters.
 	numPending int32 // number of requests pending assignment or block response
 	// peers
-	peers map[string]*bpPeer
+	peers         map[string]*bpPeer
+	maxPeerHeight int64
 
 	requestsCh chan<- BlockRequest
 	timeoutsCh chan<- string
 }
 
-func NewBlockPool(start int, requestsCh chan<- BlockRequest, timeoutsCh chan<- string) *BlockPool {
+func NewBlockPool(start int64, requestsCh chan<- BlockRequest, timeoutsCh chan<- string) *BlockPool {
 	bp := &BlockPool{
 		peers: make(map[string]*bpPeer),
 
-		requesters: make(map[int]*bpRequester),
+		requesters: make(map[int64]*bpRequester),
 		height:     start,
 		numPending: 0,
 
 		requestsCh: requestsCh,
 		timeoutsCh: timeoutsCh,
 	}
-	bp.QuitService = *NewQuitService(log, "BlockPool", bp)
+	bp.BaseService = *cmn.NewBaseService(nil, "BlockPool", bp)
 	return bp
 }
 
 func (pool *BlockPool) OnStart() error {
-	pool.QuitService.OnStart()
 	go pool.makeRequestersRoutine()
 	pool.startTime = time.Now()
 	return nil
 }
 
-func (pool *BlockPool) OnStop() {
-	pool.QuitService.OnStop()
-}
+func (pool *BlockPool) OnStop() {}
 
 // Run spawns requesters as needed.
 func (pool *BlockPool) makeRequestersRoutine() {
+
 	for {
 		if !pool.IsRunning() {
 			break
 		}
+
 		_, numPending, lenRequesters := pool.GetStatus()
 		if numPending >= maxPendingRequests {
 			// sleep for a bit.
@@ -107,7 +122,7 @@ func (pool *BlockPool) removeTimedoutPeers() {
 			// XXX remove curRate != 0
 			if curRate != 0 && curRate < minRecvRate {
 				pool.sendTimeout(peer.id)
-				log.Warn("SendTimeout", "peer", peer.id, "reason", "curRate too low")
+				pool.Logger.Error("SendTimeout", "peer", peer.id, "reason", "curRate too low")
 				peer.didTimeout = true
 			}
 		}
@@ -117,7 +132,7 @@ func (pool *BlockPool) removeTimedoutPeers() {
 	}
 }
 
-func (pool *BlockPool) GetStatus() (height int, numPending int32, lenRequesters int) {
+func (pool *BlockPool) GetStatus() (height int64, numPending int32, lenRequesters int) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -129,21 +144,16 @@ func (pool *BlockPool) IsCaughtUp() bool {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	height := pool.height
-
 	// Need at least 1 peer to be considered caught up.
 	if len(pool.peers) == 0 {
-		log.Debug("Blockpool has no peers")
+		pool.Logger.Debug("Blockpool has no peers")
 		return false
 	}
 
-	maxPeerHeight := 0
-	for _, peer := range pool.peers {
-		maxPeerHeight = MaxInt(maxPeerHeight, peer.height)
-	}
-
-	isCaughtUp := (height > 0 || time.Now().Sub(pool.startTime) > 5*time.Second) && (maxPeerHeight == 0 || height >= maxPeerHeight)
-	log.Notice(Fmt("IsCaughtUp: %v", isCaughtUp), "height", height, "maxPeerHeight", maxPeerHeight)
+	// some conditions to determine if we're caught up
+	receivedBlockOrTimedOut := (pool.height > 0 || time.Since(pool.startTime) > 5*time.Second)
+	ourChainIsLongestAmongPeers := pool.maxPeerHeight == 0 || pool.height >= pool.maxPeerHeight
+	isCaughtUp := receivedBlockOrTimedOut && ourChainIsLongestAmongPeers
 	return isCaughtUp
 }
 
@@ -179,23 +189,24 @@ func (pool *BlockPool) PopRequest() {
 		delete(pool.requesters, pool.height)
 		pool.height++
 	} else {
-		PanicSanity(Fmt("Expected requester to pop, got nothing at height %v", pool.height))
+		cmn.PanicSanity(cmn.Fmt("Expected requester to pop, got nothing at height %v", pool.height))
 	}
 }
 
 // Invalidates the block at pool.height,
 // Remove the peer and redo request from others.
-func (pool *BlockPool) RedoRequest(height int) {
+func (pool *BlockPool) RedoRequest(height int64) {
 	pool.mtx.Lock()
+	defer pool.mtx.Unlock()
+
 	request := pool.requesters[height]
-	pool.mtx.Unlock()
 
 	if request.block == nil {
-		PanicSanity("Expected block to be non-nil")
+		cmn.PanicSanity("Expected block to be non-nil")
 	}
 	// RemovePeer will redo all requesters associated with this peer.
 	// TODO: record this malfeasance
-	pool.RemovePeer(request.peerID)
+	pool.removePeer(request.peerID)
 }
 
 // TODO: ensure that blocks come in order for each peer.
@@ -205,20 +216,31 @@ func (pool *BlockPool) AddBlock(peerID string, block *types.Block, blockSize int
 
 	requester := pool.requesters[block.Height]
 	if requester == nil {
+		// a block we didn't expect.
+		// TODO:if height is too far ahead, punish peer
 		return
 	}
 
 	if requester.setBlock(block, peerID) {
 		pool.numPending--
 		peer := pool.peers[peerID]
-		peer.decrPending(blockSize)
+		if peer != nil {
+			peer.decrPending(blockSize)
+		}
 	} else {
 		// Bad peer?
 	}
 }
 
+// MaxPeerHeight returns the highest height reported by a peer.
+func (pool *BlockPool) MaxPeerHeight() int64 {
+	pool.mtx.Lock()
+	defer pool.mtx.Unlock()
+	return pool.maxPeerHeight
+}
+
 // Sets the peer's alleged blockchain height.
-func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
+func (pool *BlockPool) SetPeerHeight(peerID string, height int64) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -227,8 +249,13 @@ func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
 		peer.height = height
 	} else {
 		peer = newBPPeer(pool, peerID, height)
+		peer.setLogger(pool.Logger.With("peer", peerID))
 		pool.peers[peerID] = peer
 	}
+
+	if height > pool.maxPeerHeight {
+		pool.maxPeerHeight = height
+	}
 }
 
 func (pool *BlockPool) RemovePeer(peerID string) {
@@ -241,7 +268,9 @@ func (pool *BlockPool) RemovePeer(peerID string) {
 func (pool *BlockPool) removePeer(peerID string) {
 	for _, requester := range pool.requesters {
 		if requester.getPeerID() == peerID {
-			pool.numPending++
+			if requester.getBlock() != nil {
+				pool.numPending++
+			}
 			go requester.redo() // pick another peer and ...
 		}
 	}
@@ -250,7 +279,7 @@ func (pool *BlockPool) removePeer(peerID string) {
 
 // Pick an available peer with at least the given minHeight.
 // If no peers are available, returns nil.
-func (pool *BlockPool) pickIncrAvailablePeer(minHeight int) *bpPeer {
+func (pool *BlockPool) pickIncrAvailablePeer(minHeight int64) *bpPeer {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -258,7 +287,6 @@ func (pool *BlockPool) pickIncrAvailablePeer(minHeight int) *bpPeer {
 		if peer.didTimeout {
 			pool.removePeer(peer.id)
 			continue
-		} else {
 		}
 		if peer.numPending >= maxPendingRequestsPerPeer {
 			continue
@@ -276,16 +304,24 @@ func (pool *BlockPool) makeNextRequester() {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	nextHeight := pool.height + len(pool.requesters)
+	nextHeight := pool.height + pool.requestersLen()
 	request := newBPRequester(pool, nextHeight)
+	// request.SetLogger(pool.Logger.With("height", nextHeight))
 
 	pool.requesters[nextHeight] = request
 	pool.numPending++
 
-	request.Start()
+	err := request.Start()
+	if err != nil {
+		request.Logger.Error("Error starting request", "err", err)
+	}
 }
 
-func (pool *BlockPool) sendRequest(height int, peerID string) {
+func (pool *BlockPool) requestersLen() int64 {
+	return int64(len(pool.requesters))
+}
+
+func (pool *BlockPool) sendRequest(height int64, peerID string) {
 	if !pool.IsRunning() {
 		return
 	}
@@ -299,17 +335,19 @@ func (pool *BlockPool) sendTimeout(peerID string) {
 	pool.timeoutsCh <- peerID
 }
 
+// unused by tendermint; left for debugging purposes
 func (pool *BlockPool) debug() string {
 	pool.mtx.Lock() // Lock
 	defer pool.mtx.Unlock()
 
 	str := ""
-	for h := pool.height; h < pool.height+len(pool.requesters); h++ {
+	nextHeight := pool.height + pool.requestersLen()
+	for h := pool.height; h < nextHeight; h++ {
 		if pool.requesters[h] == nil {
-			str += Fmt("H(%v):X ", h)
+			str += cmn.Fmt("H(%v):X ", h)
 		} else {
-			str += Fmt("H(%v):", h)
-			str += Fmt("B?(%v) ", pool.requesters[h].block != nil)
+			str += cmn.Fmt("H(%v):", h)
+			str += cmn.Fmt("B?(%v) ", pool.requesters[h].block != nil)
 		}
 	}
 	return str
@@ -322,26 +360,32 @@ type bpPeer struct {
 	id          string
 	recvMonitor *flow.Monitor
 
-	mtx        sync.Mutex
-	height     int
+	height     int64
 	numPending int32
 	timeout    *time.Timer
 	didTimeout bool
+
+	logger log.Logger
 }
 
-func newBPPeer(pool *BlockPool, peerID string, height int) *bpPeer {
+func newBPPeer(pool *BlockPool, peerID string, height int64) *bpPeer {
 	peer := &bpPeer{
 		pool:       pool,
 		id:         peerID,
 		height:     height,
 		numPending: 0,
+		logger:     log.NewNopLogger(),
 	}
 	return peer
 }
 
+func (peer *bpPeer) setLogger(l log.Logger) {
+	peer.logger = l
+}
+
 func (peer *bpPeer) resetMonitor() {
 	peer.recvMonitor = flow.New(time.Second, time.Second*40)
-	var initialValue = float64(minRecvRate) * math.E
+	initialValue := float64(minRecvRate) * math.E
 	peer.recvMonitor.SetREMA(initialValue)
 }
 
@@ -376,16 +420,16 @@ func (peer *bpPeer) onTimeout() {
 	defer peer.pool.mtx.Unlock()
 
 	peer.pool.sendTimeout(peer.id)
-	log.Warn("SendTimeout", "peer", peer.id, "reason", "onTimeout")
+	peer.logger.Error("SendTimeout", "reason", "onTimeout")
 	peer.didTimeout = true
 }
 
 //-------------------------------------
 
 type bpRequester struct {
-	QuitService
+	cmn.BaseService
 	pool       *BlockPool
-	height     int
+	height     int64
 	gotBlockCh chan struct{}
 	redoCh     chan struct{}
 
@@ -394,7 +438,7 @@ type bpRequester struct {
 	block  *types.Block
 }
 
-func newBPRequester(pool *BlockPool, height int) *bpRequester {
+func newBPRequester(pool *BlockPool, height int64) *bpRequester {
 	bpr := &bpRequester{
 		pool:       pool,
 		height:     height,
@@ -404,12 +448,11 @@ func newBPRequester(pool *BlockPool, height int) *bpRequester {
 		peerID: "",
 		block:  nil,
 	}
-	bpr.QuitService = *NewQuitService(nil, "bpRequester", bpr)
+	bpr.BaseService = *cmn.NewBaseService(nil, "bpRequester", bpr)
 	return bpr
 }
 
 func (bpr *bpRequester) OnStart() error {
-	bpr.QuitService.OnStart()
 	go bpr.requestRoutine()
 	return nil
 }
@@ -507,6 +550,6 @@ OUTER_LOOP:
 //-------------------------------------
 
 type BlockRequest struct {
-	Height int
+	Height int64
 	PeerID string
 }

blockchain/pool_test.go

@@ -5,8 +5,9 @@ import (
 	"testing"
 	"time"
 
-	. "github.com/tendermint/go-common"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 )
 
 func init() {
@@ -15,26 +16,33 @@ func init() {
 
 type testPeer struct {
 	id     string
-	height int
+	height int64
 }
 
-func makePeers(numPeers int, minHeight, maxHeight int) map[string]testPeer {
+func makePeers(numPeers int, minHeight, maxHeight int64) map[string]testPeer {
 	peers := make(map[string]testPeer, numPeers)
 	for i := 0; i < numPeers; i++ {
-		peerID := RandStr(12)
-		height := minHeight + rand.Intn(maxHeight-minHeight)
+		peerID := cmn.RandStr(12)
+		height := minHeight + rand.Int63n(maxHeight-minHeight)
 		peers[peerID] = testPeer{peerID, height}
 	}
 	return peers
 }
 
 func TestBasic(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
 	timeoutsCh := make(chan string, 100)
 	requestsCh := make(chan BlockRequest, 100)
 	pool := NewBlockPool(start, requestsCh, timeoutsCh)
-	pool.Start()
+	pool.SetLogger(log.TestingLogger())
+
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
+
+	defer pool.Stop()
 
 	// Introduce each peer.
 	go func() {
@@ -64,7 +72,7 @@ func TestBasic(t *testing.T) {
 		case peerID := <-timeoutsCh:
 			t.Errorf("timeout: %v", peerID)
 		case request := <-requestsCh:
-			log.Info("TEST: Pulled new BlockRequest", "request", request)
+			t.Logf("Pulled new BlockRequest %v", request)
 			if request.Height == 300 {
 				return // Done!
 			}
@@ -72,24 +80,27 @@ func TestBasic(t *testing.T) {
 			go func() {
 				block := &types.Block{Header: &types.Header{Height: request.Height}}
 				pool.AddBlock(request.PeerID, block, 123)
-				log.Info("TEST: Added block", "block", request.Height, "peer", request.PeerID)
+				t.Logf("Added block from peer %v (height: %v)", request.PeerID, request.Height)
 			}()
 		}
 	}
-
-	pool.Stop()
 }
 
 func TestTimeout(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
 	timeoutsCh := make(chan string, 100)
 	requestsCh := make(chan BlockRequest, 100)
 	pool := NewBlockPool(start, requestsCh, timeoutsCh)
-	pool.Start()
+	pool.SetLogger(log.TestingLogger())
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
+	defer pool.Stop()
 
 	for _, peer := range peers {
-		log.Info("Peer", "id", peer.id)
+		t.Logf("Peer %v", peer.id)
 	}
 
 	// Introduce each peer.
@@ -120,7 +131,7 @@ func TestTimeout(t *testing.T) {
 	for {
 		select {
 		case peerID := <-timeoutsCh:
-			log.Info("Timeout", "peerID", peerID)
+			t.Logf("Peer %v timeouted", peerID)
 			if _, ok := timedOut[peerID]; !ok {
 				counter++
 				if counter == len(peers) {
@@ -128,9 +139,7 @@ func TestTimeout(t *testing.T) {
 				}
 			}
 		case request := <-requestsCh:
-			log.Info("TEST: Pulled new BlockRequest", "request", request)
+			t.Logf("Pulled new BlockRequest %+v", request)
 		}
 	}
-
-	pool.Stop()
 }

blockchain/reactor.go

@@ -3,24 +3,24 @@ package blockchain
 import (
 	"bytes"
 	"errors"
-	"fmt"
 	"reflect"
+	"sync"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-events"
-	"github.com/tendermint/go-p2p"
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/proxy"
+	wire "github.com/tendermint/go-wire"
+	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 )
 
 const (
-	BlockchainChannel      = byte(0x40)
-	defaultChannelCapacity = 100
-	defaultSleepIntervalMS = 500
-	trySyncIntervalMS      = 100
+	// BlockchainChannel is a channel for blocks and status updates (`BlockStore` height)
+	BlockchainChannel = byte(0x40)
+
+	defaultChannelCapacity = 1000
+	trySyncIntervalMS      = 50
 	// stop syncing when last block's time is
 	// within this much of the system time.
 	// stopSyncingDurationMinutes = 10
@@ -29,39 +29,38 @@ const (
 	statusUpdateIntervalSeconds = 10
 	// check if we should switch to consensus reactor
 	switchToConsensusIntervalSeconds = 1
-	maxBlockchainResponseSize        = types.MaxBlockSize + 2
 )
 
 type consensusReactor interface {
 	// for when we switch from blockchain reactor and fast sync to
 	// the consensus machine
-	SwitchToConsensus(*sm.State)
+	SwitchToConsensus(sm.State, int)
 }
 
 // BlockchainReactor handles long-term catchup syncing.
 type BlockchainReactor struct {
 	p2p.BaseReactor
 
-	sw           *p2p.Switch
-	state        *sm.State
-	proxyAppConn proxy.AppConnConsensus // same as consensus.proxyAppConn
-	store        *BlockStore
-	pool         *BlockPool
-	fastSync     bool
-	requestsCh   chan BlockRequest
-	timeoutsCh   chan string
-	lastBlock    *types.Block
+	mtx    sync.Mutex
+	params types.ConsensusParams
 
-	evsw *events.EventSwitch
+	// immutable
+	initialState sm.State
+
+	blockExec  *sm.BlockExecutor
+	store      *BlockStore
+	pool       *BlockPool
+	fastSync   bool
+	requestsCh chan BlockRequest
+	timeoutsCh chan string
 }
 
-func NewBlockchainReactor(state *sm.State, proxyAppConn proxy.AppConnConsensus, store *BlockStore, fastSync bool) *BlockchainReactor {
-	if state.LastBlockHeight == store.Height()-1 {
-		store.height -= 1 // XXX HACK, make this better
-	}
+// NewBlockchainReactor returns new reactor instance.
+func NewBlockchainReactor(state sm.State, blockExec *sm.BlockExecutor, store *BlockStore, fastSync bool) *BlockchainReactor {
 	if state.LastBlockHeight != store.Height() {
-		PanicSanity(Fmt("state (%v) and store (%v) height mismatch", state.LastBlockHeight, store.Height()))
+		cmn.PanicSanity(cmn.Fmt("state (%v) and store (%v) height mismatch", state.LastBlockHeight, store.Height()))
 	}
+
 	requestsCh := make(chan BlockRequest, defaultChannelCapacity)
 	timeoutsCh := make(chan string, defaultChannelCapacity)
 	pool := NewBlockPool(
@@ -70,22 +69,32 @@ func NewBlockchainReactor(state *sm.State, proxyAppConn proxy.AppConnConsensus,
 		timeoutsCh,
 	)
 	bcR := &BlockchainReactor{
-		state:        state,
-		proxyAppConn: proxyAppConn,
+		params:       state.ConsensusParams,
+		initialState: state,
+		blockExec:    blockExec,
 		store:        store,
 		pool:         pool,
 		fastSync:     fastSync,
 		requestsCh:   requestsCh,
 		timeoutsCh:   timeoutsCh,
 	}
-	bcR.BaseReactor = *p2p.NewBaseReactor(log, "BlockchainReactor", bcR)
+	bcR.BaseReactor = *p2p.NewBaseReactor("BlockchainReactor", bcR)
 	return bcR
 }
 
+// SetLogger implements cmn.Service by setting the logger on reactor and pool.
+func (bcR *BlockchainReactor) SetLogger(l log.Logger) {
+	bcR.BaseService.Logger = l
+	bcR.pool.Logger = l
+}
+
+// OnStart implements cmn.Service.
 func (bcR *BlockchainReactor) OnStart() error {
-	bcR.BaseReactor.OnStart()
+	if err := bcR.BaseReactor.OnStart(); err != nil {
+		return err
+	}
 	if bcR.fastSync {
-		_, err := bcR.pool.Start()
+		err := bcR.pool.Start()
 		if err != nil {
 			return err
 		}
@@ -94,60 +103,74 @@ func (bcR *BlockchainReactor) OnStart() error {
 	return nil
 }
 
+// OnStop implements cmn.Service.
 func (bcR *BlockchainReactor) OnStop() {
 	bcR.BaseReactor.OnStop()
 	bcR.pool.Stop()
 }
 
-// Implements Reactor
+// GetChannels implements Reactor
 func (bcR *BlockchainReactor) GetChannels() []*p2p.ChannelDescriptor {
 	return []*p2p.ChannelDescriptor{
-		&p2p.ChannelDescriptor{
+		{
 			ID:                BlockchainChannel,
-			Priority:          5,
-			SendQueueCapacity: 100,
+			Priority:          10,
+			SendQueueCapacity: 1000,
 		},
 	}
 }
 
-// Implements Reactor
-func (bcR *BlockchainReactor) AddPeer(peer *p2p.Peer) {
-	// Send peer our state.
-	peer.Send(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}})
+// AddPeer implements Reactor by sending our state to peer.
+func (bcR *BlockchainReactor) AddPeer(peer p2p.Peer) {
+	if !peer.Send(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}}) {
+		// doing nothing, will try later in `poolRoutine`
+	}
+	// peer is added to the pool once we receive the first
+	// bcStatusResponseMessage from the peer and call pool.SetPeerHeight
 }
 
-// Implements Reactor
-func (bcR *BlockchainReactor) RemovePeer(peer *p2p.Peer, reason interface{}) {
-	// Remove peer from the pool.
-	bcR.pool.RemovePeer(peer.Key)
+// RemovePeer implements Reactor by removing peer from the pool.
+func (bcR *BlockchainReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
+	bcR.pool.RemovePeer(peer.Key())
 }
 
-// Implements Reactor
-func (bcR *BlockchainReactor) Receive(chID byte, src *p2p.Peer, msgBytes []byte) {
-	_, msg, err := DecodeMessage(msgBytes)
+// respondToPeer loads a block and sends it to the requesting peer,
+// if we have it. Otherwise, we'll respond saying we don't have it.
+// According to the Tendermint spec, if all nodes are honest,
+// no node should be requesting for a block that's non-existent.
+func (bcR *BlockchainReactor) respondToPeer(msg *bcBlockRequestMessage, src p2p.Peer) (queued bool) {
+	block := bcR.store.LoadBlock(msg.Height)
+	if block != nil {
+		msg := &bcBlockResponseMessage{Block: block}
+		return src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{msg})
+	}
+
+	bcR.Logger.Info("Peer asking for a block we don't have", "src", src, "height", msg.Height)
+
+	return src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{
+		&bcNoBlockResponseMessage{Height: msg.Height},
+	})
+}
+
+// Receive implements Reactor by handling 4 types of messages (look below).
+func (bcR *BlockchainReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
+	_, msg, err := DecodeMessage(msgBytes, bcR.maxMsgSize())
 	if err != nil {
-		log.Warn("Error decoding message", "error", err)
+		bcR.Logger.Error("Error decoding message", "err", err)
 		return
 	}
 
-	log.Notice("Receive", "src", src, "chID", chID, "msg", msg)
+	bcR.Logger.Debug("Receive", "src", src, "chID", chID, "msg", msg)
 
+	// TODO: improve logic to satisfy megacheck
 	switch msg := msg.(type) {
 	case *bcBlockRequestMessage:
-		// Got a request for a block. Respond with block if we have it.
-		block := bcR.store.LoadBlock(msg.Height)
-		if block != nil {
-			msg := &bcBlockResponseMessage{Block: block}
-			queued := src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{msg})
-			if !queued {
-				// queue is full, just ignore.
-			}
-		} else {
-			// TODO peer is asking for things we don't have.
+		if queued := bcR.respondToPeer(msg, src); !queued {
+			// Unfortunately not queued since the queue is full.
 		}
 	case *bcBlockResponseMessage:
 		// Got a block.
-		bcR.pool.AddBlock(src.Key, msg.Block, len(msgBytes))
+		bcR.pool.AddBlock(src.Key(), msg.Block, len(msgBytes))
 	case *bcStatusRequestMessage:
 		// Send peer our state.
 		queued := src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}})
@@ -156,12 +179,27 @@ func (bcR *BlockchainReactor) Receive(chID byte, src *p2p.Peer, msgBytes []byte)
 		}
 	case *bcStatusResponseMessage:
 		// Got a peer status. Unverified.
-		bcR.pool.SetPeerHeight(src.Key, msg.Height)
+		bcR.pool.SetPeerHeight(src.Key(), msg.Height)
 	default:
-		log.Warn(Fmt("Unknown message type %v", reflect.TypeOf(msg)))
+		bcR.Logger.Error(cmn.Fmt("Unknown message type %v", reflect.TypeOf(msg)))
 	}
 }
 
+// maxMsgSize returns the maximum allowable size of a
+// message on the blockchain reactor.
+func (bcR *BlockchainReactor) maxMsgSize() int {
+	bcR.mtx.Lock()
+	defer bcR.mtx.Unlock()
+	return bcR.params.BlockSize.MaxBytes + 2
+}
+
+// updateConsensusParams updates the internal consensus params
+func (bcR *BlockchainReactor) updateConsensusParams(params types.ConsensusParams) {
+	bcR.mtx.Lock()
+	defer bcR.mtx.Unlock()
+	bcR.params = params
+}
+
 // Handle messages from the poolReactor telling the reactor what to do.
 // NOTE: Don't sleep in the FOR_LOOP or otherwise slow it down!
 // (Except for the SYNC_LOOP, which is the primary purpose and must be synchronous.)
@@ -171,6 +209,14 @@ func (bcR *BlockchainReactor) poolRoutine() {
 	statusUpdateTicker := time.NewTicker(statusUpdateIntervalSeconds * time.Second)
 	switchToConsensusTicker := time.NewTicker(switchToConsensusIntervalSeconds * time.Second)
 
+	blocksSynced := 0
+
+	chainID := bcR.initialState.ChainID
+	state := bcR.initialState
+
+	lastHundred := time.Now()
+	lastRate := 0.0
+
 FOR_LOOP:
 	for {
 		select {
@@ -192,62 +238,72 @@ FOR_LOOP:
 			if peer != nil {
 				bcR.Switch.StopPeerForError(peer, errors.New("BlockchainReactor Timeout"))
 			}
-		case _ = <-statusUpdateTicker.C:
+		case <-statusUpdateTicker.C:
 			// ask for status updates
-			go bcR.BroadcastStatusRequest()
-		case _ = <-switchToConsensusTicker.C:
-			height, numPending, _ := bcR.pool.GetStatus()
+			go bcR.BroadcastStatusRequest() // nolint: errcheck
+		case <-switchToConsensusTicker.C:
+			height, numPending, lenRequesters := bcR.pool.GetStatus()
 			outbound, inbound, _ := bcR.Switch.NumPeers()
-			log.Info("Consensus ticker", "numPending", numPending, "total", len(bcR.pool.requesters),
+			bcR.Logger.Debug("Consensus ticker", "numPending", numPending, "total", lenRequesters,
 				"outbound", outbound, "inbound", inbound)
 			if bcR.pool.IsCaughtUp() {
-				log.Notice("Time to switch to consensus reactor!", "height", height)
+				bcR.Logger.Info("Time to switch to consensus reactor!", "height", height)
 				bcR.pool.Stop()
 
 				conR := bcR.Switch.Reactor("CONSENSUS").(consensusReactor)
-				conR.SwitchToConsensus(bcR.state)
+				conR.SwitchToConsensus(state, blocksSynced)
 
 				break FOR_LOOP
 			}
-		case _ = <-trySyncTicker.C: // chan time
+		case <-trySyncTicker.C: // chan time
 			// This loop can be slow as long as it's doing syncing work.
 		SYNC_LOOP:
 			for i := 0; i < 10; i++ {
 				// See if there are any blocks to sync.
 				first, second := bcR.pool.PeekTwoBlocks()
-				//log.Info("TrySync peeked", "first", first, "second", second)
+				//bcR.Logger.Info("TrySync peeked", "first", first, "second", second)
 				if first == nil || second == nil {
 					// We need both to sync the first block.
 					break SYNC_LOOP
 				}
-				firstParts := first.MakePartSet()
+				firstParts := first.MakePartSet(state.ConsensusParams.BlockPartSizeBytes)
 				firstPartsHeader := firstParts.Header()
+				firstID := types.BlockID{first.Hash(), firstPartsHeader}
 				// Finally, verify the first block using the second's commit
-				err := bcR.state.Validators.VerifyCommit(
-					bcR.state.ChainID, first.Hash(), firstPartsHeader, first.Height, second.LastCommit)
+				// NOTE: we can probably make this more efficient, but note that calling
+				// first.Hash() doesn't verify the tx contents, so MakePartSet() is
+				// currently necessary.
+				err := state.Validators.VerifyCommit(
+					chainID, firstID, first.Height, second.LastCommit)
 				if err != nil {
-					log.Info("error in validation", "error", err)
+					bcR.Logger.Error("Error in validation", "err", err)
 					bcR.pool.RedoRequest(first.Height)
 					break SYNC_LOOP
 				} else {
 					bcR.pool.PopRequest()
-					// TODO: use ApplyBlock instead of Exec/Commit/SetAppHash/Save
-					err := bcR.state.ExecBlock(bcR.evsw, bcR.proxyAppConn, first, firstPartsHeader)
-					if err != nil {
-						// TODO This is bad, are we zombie?
-						PanicQ(Fmt("Failed to process committed block (%d:%X): %v", first.Height, first.Hash(), err))
-					}
+
+					bcR.store.SaveBlock(first, firstParts, second.LastCommit)
+
 					// NOTE: we could improve performance if we
 					// didn't make the app commit to disk every block
 					// ... but we would need a way to get the hash without it persisting
-					res := bcR.proxyAppConn.CommitSync()
-					if res.IsErr() {
-						// TODO Handle gracefully.
-						PanicQ(Fmt("Failed to commit block at application: %v", res))
+					var err error
+					state, err = bcR.blockExec.ApplyBlock(state, firstID, first)
+					if err != nil {
+						// TODO This is bad, are we zombie?
+						cmn.PanicQ(cmn.Fmt("Failed to process committed block (%d:%X): %v", first.Height, first.Hash(), err))
+					}
+					blocksSynced += 1
+
+					// update the consensus params
+					bcR.updateConsensusParams(state.ConsensusParams)
+
+					if blocksSynced%100 == 0 {
+						lastRate = 0.9*lastRate + 0.1*(100/time.Since(lastHundred).Seconds())
+						bcR.Logger.Info("Fast Sync Rate", "height", bcR.pool.height,
+							"max_peer_height", bcR.pool.MaxPeerHeight(), "blocks/s", lastRate)
+						lastHundred = time.Now()
 					}
-					bcR.store.SaveBlock(first, firstParts, second.LastCommit)
-					bcR.state.AppHash = res.Data
-					bcR.state.Save()
 				}
 			}
 			continue FOR_LOOP
@@ -257,49 +313,44 @@ FOR_LOOP:
 	}
 }
 
-func (bcR *BlockchainReactor) BroadcastStatusResponse() error {
-	bcR.Switch.Broadcast(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}})
-	return nil
-}
-
+// BroadcastStatusRequest broadcasts `BlockStore` height.
 func (bcR *BlockchainReactor) BroadcastStatusRequest() error {
 	bcR.Switch.Broadcast(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusRequestMessage{bcR.store.Height()}})
 	return nil
 }
 
-// implements events.Eventable
-func (bcR *BlockchainReactor) SetEventSwitch(evsw *events.EventSwitch) {
-	bcR.evsw = evsw
-}
-
 //-----------------------------------------------------------------------------
 // Messages
 
 const (
-	msgTypeBlockRequest   = byte(0x10)
-	msgTypeBlockResponse  = byte(0x11)
-	msgTypeStatusResponse = byte(0x20)
-	msgTypeStatusRequest  = byte(0x21)
+	msgTypeBlockRequest    = byte(0x10)
+	msgTypeBlockResponse   = byte(0x11)
+	msgTypeNoBlockResponse = byte(0x12)
+	msgTypeStatusResponse  = byte(0x20)
+	msgTypeStatusRequest   = byte(0x21)
 )
 
+// BlockchainMessage is a generic message for this reactor.
 type BlockchainMessage interface{}
 
 var _ = wire.RegisterInterface(
 	struct{ BlockchainMessage }{},
 	wire.ConcreteType{&bcBlockRequestMessage{}, msgTypeBlockRequest},
 	wire.ConcreteType{&bcBlockResponseMessage{}, msgTypeBlockResponse},
+	wire.ConcreteType{&bcNoBlockResponseMessage{}, msgTypeNoBlockResponse},
 	wire.ConcreteType{&bcStatusResponseMessage{}, msgTypeStatusResponse},
 	wire.ConcreteType{&bcStatusRequestMessage{}, msgTypeStatusRequest},
 )
 
+// DecodeMessage decodes BlockchainMessage.
 // TODO: ensure that bz is completely read.
-func DecodeMessage(bz []byte) (msgType byte, msg BlockchainMessage, err error) {
+func DecodeMessage(bz []byte, maxSize int) (msgType byte, msg BlockchainMessage, err error) {
 	msgType = bz[0]
 	n := int(0)
 	r := bytes.NewReader(bz)
-	msg = wire.ReadBinary(struct{ BlockchainMessage }{}, r, maxBlockchainResponseSize, &n, &err).(struct{ BlockchainMessage }).BlockchainMessage
+	msg = wire.ReadBinary(struct{ BlockchainMessage }{}, r, maxSize, &n, &err).(struct{ BlockchainMessage }).BlockchainMessage
 	if err != nil && n != len(bz) {
-		err = errors.New("DecodeMessage() had bytes left over.")
+		err = errors.New("DecodeMessage() had bytes left over")
 	}
 	return
 }
@@ -307,11 +358,19 @@ func DecodeMessage(bz []byte) (msgType byte, msg BlockchainMessage, err error) {
 //-------------------------------------
 
 type bcBlockRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcBlockRequestMessage) String() string {
-	return fmt.Sprintf("[bcBlockRequestMessage %v]", m.Height)
+	return cmn.Fmt("[bcBlockRequestMessage %v]", m.Height)
+}
+
+type bcNoBlockResponseMessage struct {
+	Height int64
+}
+
+func (brm *bcNoBlockResponseMessage) String() string {
+	return cmn.Fmt("[bcNoBlockResponseMessage %d]", brm.Height)
 }
 
 //-------------------------------------
@@ -322,25 +381,25 @@ type bcBlockResponseMessage struct {
 }
 
 func (m *bcBlockResponseMessage) String() string {
-	return fmt.Sprintf("[bcBlockResponseMessage %v]", m.Block.Height)
+	return cmn.Fmt("[bcBlockResponseMessage %v]", m.Block.Height)
 }
 
 //-------------------------------------
 
 type bcStatusRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusRequestMessage) String() string {
-	return fmt.Sprintf("[bcStatusRequestMessage %v]", m.Height)
+	return cmn.Fmt("[bcStatusRequestMessage %v]", m.Height)
 }
 
 //-------------------------------------
 
 type bcStatusResponseMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusResponseMessage) String() string {
-	return fmt.Sprintf("[bcStatusResponseMessage %v]", m.Height)
+	return cmn.Fmt("[bcStatusResponseMessage %v]", m.Height)
 }

blockchain/reactor_test.go

@@ -0,0 +1,151 @@
+package blockchain
+
+import (
+	"testing"
+
+	wire "github.com/tendermint/go-wire"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+)
+
+func makeStateAndBlockStore(logger log.Logger) (sm.State, *BlockStore) {
+	config := cfg.ResetTestRoot("blockchain_reactor_test")
+	blockStore := NewBlockStore(dbm.NewMemDB())
+	state, _ := sm.LoadStateFromDBOrGenesisFile(dbm.NewMemDB(), config.GenesisFile())
+	return state, blockStore
+}
+
+func newBlockchainReactor(logger log.Logger, maxBlockHeight int64) *BlockchainReactor {
+	state, blockStore := makeStateAndBlockStore(logger)
+
+	// Make the blockchainReactor itself
+	fastSync := true
+	var nilApp proxy.AppConnConsensus
+	blockExec := sm.NewBlockExecutor(dbm.NewMemDB(), log.TestingLogger(), nilApp, types.MockMempool{}, types.MockEvidencePool{})
+
+	bcReactor := NewBlockchainReactor(state.Copy(), blockExec, blockStore, fastSync)
+	bcReactor.SetLogger(logger.With("module", "blockchain"))
+
+	// Next: we need to set a switch in order for peers to be added in
+	bcReactor.Switch = p2p.NewSwitch(cfg.DefaultP2PConfig())
+
+	// Lastly: let's add some blocks in
+	for blockHeight := int64(1); blockHeight <= maxBlockHeight; blockHeight++ {
+		firstBlock := makeBlock(blockHeight, state)
+		secondBlock := makeBlock(blockHeight+1, state)
+		firstParts := firstBlock.MakePartSet(state.ConsensusParams.BlockGossip.BlockPartSizeBytes)
+		blockStore.SaveBlock(firstBlock, firstParts, secondBlock.LastCommit)
+	}
+
+	return bcReactor
+}
+
+func TestNoBlockMessageResponse(t *testing.T) {
+	maxBlockHeight := int64(20)
+
+	bcr := newBlockchainReactor(log.TestingLogger(), maxBlockHeight)
+	bcr.Start()
+	defer bcr.Stop()
+
+	// Add some peers in
+	peer := newbcrTestPeer(cmn.RandStr(12))
+	bcr.AddPeer(peer)
+
+	chID := byte(0x01)
+
+	tests := []struct {
+		height   int64
+		existent bool
+	}{
+		{maxBlockHeight + 2, false},
+		{10, true},
+		{1, true},
+		{100, false},
+	}
+
+	// receive a request message from peer,
+	// wait to hear response
+	for _, tt := range tests {
+		reqBlockMsg := &bcBlockRequestMessage{tt.height}
+		reqBlockBytes := wire.BinaryBytes(struct{ BlockchainMessage }{reqBlockMsg})
+		bcr.Receive(chID, peer, reqBlockBytes)
+		value := peer.lastValue()
+		msg := value.(struct{ BlockchainMessage }).BlockchainMessage
+
+		if tt.existent {
+			if blockMsg, ok := msg.(*bcBlockResponseMessage); !ok {
+				t.Fatalf("Expected to receive a block response for height %d", tt.height)
+			} else if blockMsg.Block.Height != tt.height {
+				t.Fatalf("Expected response to be for height %d, got %d", tt.height, blockMsg.Block.Height)
+			}
+		} else {
+			if noBlockMsg, ok := msg.(*bcNoBlockResponseMessage); !ok {
+				t.Fatalf("Expected to receive a no block response for height %d", tt.height)
+			} else if noBlockMsg.Height != tt.height {
+				t.Fatalf("Expected response to be for height %d, got %d", tt.height, noBlockMsg.Height)
+			}
+		}
+	}
+}
+
+//----------------------------------------------
+// utility funcs
+
+func makeTxs(height int64) (txs []types.Tx) {
+	for i := 0; i < 10; i++ {
+		txs = append(txs, types.Tx([]byte{byte(height), byte(i)}))
+	}
+	return txs
+}
+
+func makeBlock(height int64, state sm.State) *types.Block {
+	block, _ := state.MakeBlock(height, makeTxs(height), new(types.Commit))
+	return block
+}
+
+// The Test peer
+type bcrTestPeer struct {
+	cmn.Service
+	key string
+	ch  chan interface{}
+}
+
+var _ p2p.Peer = (*bcrTestPeer)(nil)
+
+func newbcrTestPeer(key string) *bcrTestPeer {
+	return &bcrTestPeer{
+		Service: cmn.NewBaseService(nil, "bcrTestPeer", nil),
+		key:     key,
+		ch:      make(chan interface{}, 2),
+	}
+}
+
+func (tp *bcrTestPeer) lastValue() interface{} { return <-tp.ch }
+
+func (tp *bcrTestPeer) TrySend(chID byte, value interface{}) bool {
+	if _, ok := value.(struct{ BlockchainMessage }).BlockchainMessage.(*bcStatusResponseMessage); ok {
+		// Discard status response messages since they skew our results
+		// We only want to deal with:
+		// + bcBlockResponseMessage
+		// + bcNoBlockResponseMessage
+	} else {
+		tp.ch <- value
+	}
+	return true
+}
+
+func (tp *bcrTestPeer) Send(chID byte, data interface{}) bool { return tp.TrySend(chID, data) }
+func (tp *bcrTestPeer) NodeInfo() *p2p.NodeInfo               { return nil }
+func (tp *bcrTestPeer) Status() p2p.ConnectionStatus          { return p2p.ConnectionStatus{} }
+func (tp *bcrTestPeer) Key() string                           { return tp.key }
+func (tp *bcrTestPeer) IsOutbound() bool                      { return false }
+func (tp *bcrTestPeer) IsPersistent() bool                    { return true }
+func (tp *bcrTestPeer) Get(s string) interface{}              { return s }
+func (tp *bcrTestPeer) Set(string, interface{})               {}

blockchain/store.go

@@ -5,15 +5,16 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"sync"
 
-	. "github.com/tendermint/go-common"
-	dbm "github.com/tendermint/go-db"
-	"github.com/tendermint/go-wire"
+	wire "github.com/tendermint/go-wire"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
 )
 
 /*
-Simple low level store for blocks.
+BlockStore is a simple low level store for blocks.
 
 There are three types of information stored:
  - BlockMeta:   Meta information about each block
@@ -22,15 +23,20 @@ There are three types of information stored:
 
 Currently the precommit signatures are duplicated in the Block parts as
 well as the Commit.  In the future this may change, perhaps by moving
-the Commit data outside the Block.
+the Commit data outside the Block. (TODO)
 
-Panics indicate probable corruption in the data
+// NOTE: BlockStore methods will panic if they encounter errors
+// deserializing loaded data, indicating probable corruption on disk.
 */
 type BlockStore struct {
-	height int
-	db     dbm.DB
+	db dbm.DB
+
+	mtx    sync.RWMutex
+	height int64
 }
 
+// NewBlockStore returns a new BlockStore with the given DB,
+// initialized to the last height that was committed to the DB.
 func NewBlockStore(db dbm.DB) *BlockStore {
 	bsjson := LoadBlockStoreStateJSON(db)
 	return &BlockStore{
@@ -39,11 +45,16 @@ func NewBlockStore(db dbm.DB) *BlockStore {
 	}
 }
 
-// Height() returns the last known contiguous block height.
-func (bs *BlockStore) Height() int {
+// Height returns the last known contiguous block height.
+func (bs *BlockStore) Height() int64 {
+	bs.mtx.RLock()
+	defer bs.mtx.RUnlock()
 	return bs.height
 }
 
+// GetReader returns the value associated with the given key wrapped in an io.Reader.
+// If no value is found, it returns nil.
+// It's mainly for use with wire.ReadBinary.
 func (bs *BlockStore) GetReader(key []byte) io.Reader {
 	bytez := bs.db.Get(key)
 	if bytez == nil {
@@ -52,30 +63,35 @@ func (bs *BlockStore) GetReader(key []byte) io.Reader {
 	return bytes.NewReader(bytez)
 }
 
-func (bs *BlockStore) LoadBlock(height int) *types.Block {
+// LoadBlock returns the block with the given height.
+// If no block is found for that height, it returns nil.
+func (bs *BlockStore) LoadBlock(height int64) *types.Block {
 	var n int
 	var err error
 	r := bs.GetReader(calcBlockMetaKey(height))
 	if r == nil {
 		return nil
 	}
-	meta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
+	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading block meta: %v", err))
 	}
 	bytez := []byte{}
-	for i := 0; i < meta.PartsHeader.Total; i++ {
+	for i := 0; i < blockMeta.BlockID.PartsHeader.Total; i++ {
 		part := bs.LoadBlockPart(height, i)
 		bytez = append(bytez, part.Bytes...)
 	}
 	block := wire.ReadBinary(&types.Block{}, bytes.NewReader(bytez), 0, &n, &err).(*types.Block)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading block: %v", err))
 	}
 	return block
 }
 
-func (bs *BlockStore) LoadBlockPart(height int, index int) *types.Part {
+// LoadBlockPart returns the Part at the given index
+// from the block at the given height.
+// If no part is found for the given height and index, it returns nil.
+func (bs *BlockStore) LoadBlockPart(height int64, index int) *types.Part {
 	var n int
 	var err error
 	r := bs.GetReader(calcBlockPartKey(height, index))
@@ -84,28 +100,32 @@ func (bs *BlockStore) LoadBlockPart(height int, index int) *types.Part {
 	}
 	part := wire.ReadBinary(&types.Part{}, r, 0, &n, &err).(*types.Part)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block part: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading block part: %v", err))
 	}
 	return part
 }
 
-func (bs *BlockStore) LoadBlockMeta(height int) *types.BlockMeta {
+// LoadBlockMeta returns the BlockMeta for the given height.
+// If no block is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
 	var n int
 	var err error
 	r := bs.GetReader(calcBlockMetaKey(height))
 	if r == nil {
 		return nil
 	}
-	meta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
+	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading block meta: %v", err))
 	}
-	return meta
+	return blockMeta
 }
 
-// The +2/3 and other Precommit-votes for block at `height`.
-// This Commit comes from block.LastCommit for `height+1`.
-func (bs *BlockStore) LoadBlockCommit(height int) *types.Commit {
+// LoadBlockCommit returns the Commit for the given height.
+// This commit consists of the +2/3 and other Precommit-votes for block at `height`,
+// and it comes from the block.LastCommit for `height+1`.
+// If no commit is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockCommit(height int64) *types.Commit {
 	var n int
 	var err error
 	r := bs.GetReader(calcBlockCommitKey(height))
@@ -114,13 +134,15 @@ func (bs *BlockStore) LoadBlockCommit(height int) *types.Commit {
 	}
 	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading commit: %v", err))
 	}
 	return commit
 }
 
-// NOTE: the Precommit-vote heights are for the block at `height`
-func (bs *BlockStore) LoadSeenCommit(height int) *types.Commit {
+// LoadSeenCommit returns the locally seen Commit for the given height.
+// This is useful when we've seen a commit, but there has not yet been
+// a new block at `height + 1` that includes this commit in its block.LastCommit.
+func (bs *BlockStore) LoadSeenCommit(height int64) *types.Commit {
 	var n int
 	var err error
 	r := bs.GetReader(calcSeenCommitKey(height))
@@ -129,28 +151,32 @@ func (bs *BlockStore) LoadSeenCommit(height int) *types.Commit {
 	}
 	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		cmn.PanicCrisis(cmn.Fmt("Error reading commit: %v", err))
 	}
 	return commit
 }
 
+// SaveBlock persists the given block, blockParts, and seenCommit to the underlying db.
 // blockParts: Must be parts of the block
 // seenCommit: The +2/3 precommits that were seen which committed at height.
 //             If all the nodes restart after committing a block,
 //             we need this to reload the precommits to catch-up nodes to the
 //             most recent height.  Otherwise they'd stall at H-1.
 func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
+	if block == nil {
+		cmn.PanicSanity("BlockStore can only save a non-nil block")
+	}
 	height := block.Height
-	if height != bs.height+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.height+1, height))
+	if g, w := height, bs.Height()+1; g != w {
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", w, g))
 	}
 	if !blockParts.IsComplete() {
-		PanicSanity(Fmt("BlockStore can only save complete block part sets"))
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save complete block part sets"))
 	}
 
 	// Save block meta
-	meta := types.NewBlockMeta(block, blockParts)
-	metaBytes := wire.BinaryBytes(meta)
+	blockMeta := types.NewBlockMeta(block, blockParts)
+	metaBytes := wire.BinaryBytes(blockMeta)
 	bs.db.Set(calcBlockMetaKey(height), metaBytes)
 
 	// Save block parts
@@ -163,6 +189,7 @@ func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, s
 	bs.db.Set(calcBlockCommitKey(height-1), blockCommitBytes)
 
 	// Save seen commit (seen +2/3 precommits for block)
+	// NOTE: we can delete this at a later height
 	seenCommitBytes := wire.BinaryBytes(seenCommit)
 	bs.db.Set(calcSeenCommitKey(height), seenCommitBytes)
 
@@ -170,12 +197,17 @@ func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, s
 	BlockStoreStateJSON{Height: height}.Save(bs.db)
 
 	// Done!
+	bs.mtx.Lock()
 	bs.height = height
+	bs.mtx.Unlock()
+
+	// Flush
+	bs.db.SetSync(nil, nil)
 }
 
-func (bs *BlockStore) saveBlockPart(height int, index int, part *types.Part) {
-	if height != bs.height+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.height+1, height))
+func (bs *BlockStore) saveBlockPart(height int64, index int, part *types.Part) {
+	if height != bs.Height()+1 {
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
 	}
 	partBytes := wire.BinaryBytes(part)
 	bs.db.Set(calcBlockPartKey(height, index), partBytes)
@@ -183,19 +215,19 @@ func (bs *BlockStore) saveBlockPart(height int, index int, part *types.Part) {
 
 //-----------------------------------------------------------------------------
 
-func calcBlockMetaKey(height int) []byte {
+func calcBlockMetaKey(height int64) []byte {
 	return []byte(fmt.Sprintf("H:%v", height))
 }
 
-func calcBlockPartKey(height int, partIndex int) []byte {
+func calcBlockPartKey(height int64, partIndex int) []byte {
 	return []byte(fmt.Sprintf("P:%v:%v", height, partIndex))
 }
 
-func calcBlockCommitKey(height int) []byte {
+func calcBlockCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("C:%v", height))
 }
 
-func calcSeenCommitKey(height int) []byte {
+func calcSeenCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("SC:%v", height))
 }
 
@@ -204,17 +236,20 @@ func calcSeenCommitKey(height int) []byte {
 var blockStoreKey = []byte("blockStore")
 
 type BlockStoreStateJSON struct {
-	Height int
+	Height int64
 }
 
+// Save persists the blockStore state to the database as JSON.
 func (bsj BlockStoreStateJSON) Save(db dbm.DB) {
 	bytes, err := json.Marshal(bsj)
 	if err != nil {
-		PanicSanity(Fmt("Could not marshal state bytes: %v", err))
+		cmn.PanicSanity(cmn.Fmt("Could not marshal state bytes: %v", err))
 	}
-	db.Set(blockStoreKey, bytes)
+	db.SetSync(blockStoreKey, bytes)
 }
 
+// LoadBlockStoreStateJSON returns the BlockStoreStateJSON as loaded from disk.
+// If no BlockStoreStateJSON was previously persisted, it returns the zero value.
 func LoadBlockStoreStateJSON(db dbm.DB) BlockStoreStateJSON {
 	bytes := db.Get(blockStoreKey)
 	if bytes == nil {
@@ -225,7 +260,7 @@ func LoadBlockStoreStateJSON(db dbm.DB) BlockStoreStateJSON {
 	bsj := BlockStoreStateJSON{}
 	err := json.Unmarshal(bytes, &bsj)
 	if err != nil {
-		PanicCrisis(Fmt("Could not unmarshal bytes: %X", bytes))
+		cmn.PanicCrisis(cmn.Fmt("Could not unmarshal bytes: %X", bytes))
 	}
 	return bsj
 }

blockchain/store_test.go

@@ -0,0 +1,413 @@
+package blockchain
+
+import (
+	"bytes"
+	"fmt"
+	"io/ioutil"
+	"runtime/debug"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	wire "github.com/tendermint/go-wire"
+	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+func TestLoadBlockStoreStateJSON(t *testing.T) {
+	db := db.NewMemDB()
+
+	bsj := &BlockStoreStateJSON{Height: 1000}
+	bsj.Save(db)
+
+	retrBSJ := LoadBlockStoreStateJSON(db)
+
+	assert.Equal(t, *bsj, retrBSJ, "expected the retrieved DBs to match")
+}
+
+func TestNewBlockStore(t *testing.T) {
+	db := db.NewMemDB()
+	db.Set(blockStoreKey, []byte(`{"height": 10000}`))
+	bs := NewBlockStore(db)
+	assert.Equal(t, bs.Height(), int64(10000), "failed to properly parse blockstore")
+
+	panicCausers := []struct {
+		data    []byte
+		wantErr string
+	}{
+		{[]byte("artful-doger"), "not unmarshal bytes"},
+		{[]byte(""), "unmarshal bytes"},
+		{[]byte(" "), "unmarshal bytes"},
+	}
+
+	for i, tt := range panicCausers {
+		// Expecting a panic here on trying to parse an invalid blockStore
+		_, _, panicErr := doFn(func() (interface{}, error) {
+			db.Set(blockStoreKey, tt.data)
+			_ = NewBlockStore(db)
+			return nil, nil
+		})
+		require.NotNil(t, panicErr, "#%d panicCauser: %q expected a panic", i, tt.data)
+		assert.Contains(t, panicErr.Error(), tt.wantErr, "#%d data: %q", i, tt.data)
+	}
+
+	db.Set(blockStoreKey, nil)
+	bs = NewBlockStore(db)
+	assert.Equal(t, bs.Height(), int64(0), "expecting nil bytes to be unmarshaled alright")
+}
+
+func TestBlockStoreGetReader(t *testing.T) {
+	db := db.NewMemDB()
+	// Initial setup
+	db.Set([]byte("Foo"), []byte("Bar"))
+	db.Set([]byte("Foo1"), nil)
+
+	bs := NewBlockStore(db)
+
+	tests := [...]struct {
+		key  []byte
+		want []byte
+	}{
+		0: {key: []byte("Foo"), want: []byte("Bar")},
+		1: {key: []byte("KnoxNonExistent"), want: nil},
+		2: {key: []byte("Foo1"), want: nil},
+	}
+
+	for i, tt := range tests {
+		r := bs.GetReader(tt.key)
+		if r == nil {
+			assert.Nil(t, tt.want, "#%d: expected a non-nil reader", i)
+			continue
+		}
+		slurp, err := ioutil.ReadAll(r)
+		if err != nil {
+			t.Errorf("#%d: unexpected Read err: %v", i, err)
+		} else {
+			assert.Equal(t, slurp, tt.want, "#%d: mismatch", i)
+		}
+	}
+}
+
+func freshBlockStore() (*BlockStore, db.DB) {
+	db := db.NewMemDB()
+	return NewBlockStore(db), db
+}
+
+var (
+	state, _ = makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+
+	block       = makeBlock(1, state)
+	partSet     = block.MakePartSet(2)
+	part1       = partSet.GetPart(0)
+	part2       = partSet.GetPart(1)
+	seenCommit1 = &types.Commit{Precommits: []*types.Vote{{Height: 10, Timestamp: time.Now().UTC()}}}
+)
+
+// TODO: This test should be simplified ...
+
+func TestBlockStoreSaveLoadBlock(t *testing.T) {
+	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
+
+	// check there are no blocks at various heights
+	noBlockHeights := []int64{0, -1, 100, 1000, 2}
+	for i, height := range noBlockHeights {
+		if g := bs.LoadBlock(height); g != nil {
+			t.Errorf("#%d: height(%d) got a block; want nil", i, height)
+		}
+	}
+
+	// save a block
+	block := makeBlock(bs.Height()+1, state)
+	validPartSet := block.MakePartSet(2)
+	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10, Timestamp: time.Now().UTC()}}}
+	bs.SaveBlock(block, partSet, seenCommit)
+	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
+
+	incompletePartSet := types.NewPartSetFromHeader(types.PartSetHeader{Total: 2})
+	uncontiguousPartSet := types.NewPartSetFromHeader(types.PartSetHeader{Total: 0})
+	uncontiguousPartSet.AddPart(part2, false)
+
+	header1 := types.Header{
+		Height:  1,
+		NumTxs:  100,
+		ChainID: "block_test",
+		Time:    time.Now(),
+	}
+	header2 := header1
+	header2.Height = 4
+
+	// End of setup, test data
+
+	commitAtH10 := &types.Commit{Precommits: []*types.Vote{{Height: 10, Timestamp: time.Now().UTC()}}}
+	tuples := []struct {
+		block      *types.Block
+		parts      *types.PartSet
+		seenCommit *types.Commit
+		wantErr    bool
+		wantPanic  string
+
+		corruptBlockInDB      bool
+		corruptCommitInDB     bool
+		corruptSeenCommitInDB bool
+		eraseCommitInDB       bool
+		eraseSeenCommitInDB   bool
+	}{
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+		},
+
+		{
+			block:     nil,
+			wantPanic: "only save a non-nil block",
+		},
+
+		{
+			block:     newBlock(&header2, commitAtH10),
+			parts:     uncontiguousPartSet,
+			wantPanic: "only save contiguous blocks", // and incomplete and uncontiguous parts
+		},
+
+		{
+			block:     newBlock(&header1, commitAtH10),
+			parts:     incompletePartSet,
+			wantPanic: "only save complete block", // incomplete parts
+		},
+
+		{
+			block:             newBlock(&header1, commitAtH10),
+			parts:             validPartSet,
+			seenCommit:        seenCommit1,
+			corruptCommitInDB: true, // Corrupt the DB's commit entry
+			wantPanic:         "rror reading commit",
+		},
+
+		{
+			block:            newBlock(&header1, commitAtH10),
+			parts:            validPartSet,
+			seenCommit:       seenCommit1,
+			wantPanic:        "rror reading block",
+			corruptBlockInDB: true, // Corrupt the DB's block entry
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			// Expecting no error and we want a nil back
+			eraseSeenCommitInDB: true,
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			corruptSeenCommitInDB: true,
+			wantPanic:             "rror reading commit",
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			// Expecting no error and we want a nil back
+			eraseCommitInDB: true,
+		},
+	}
+
+	type quad struct {
+		block  *types.Block
+		commit *types.Commit
+		meta   *types.BlockMeta
+
+		seenCommit *types.Commit
+	}
+
+	for i, tuple := range tuples {
+		bs, db := freshBlockStore()
+		// SaveBlock
+		res, err, panicErr := doFn(func() (interface{}, error) {
+			bs.SaveBlock(tuple.block, tuple.parts, tuple.seenCommit)
+			if tuple.block == nil {
+				return nil, nil
+			}
+
+			if tuple.corruptBlockInDB {
+				db.Set(calcBlockMetaKey(tuple.block.Height), []byte("block-bogus"))
+			}
+			bBlock := bs.LoadBlock(tuple.block.Height)
+			bBlockMeta := bs.LoadBlockMeta(tuple.block.Height)
+
+			if tuple.eraseSeenCommitInDB {
+				db.Delete(calcSeenCommitKey(tuple.block.Height))
+			}
+			if tuple.corruptSeenCommitInDB {
+				db.Set(calcSeenCommitKey(tuple.block.Height), []byte("bogus-seen-commit"))
+			}
+			bSeenCommit := bs.LoadSeenCommit(tuple.block.Height)
+
+			commitHeight := tuple.block.Height - 1
+			if tuple.eraseCommitInDB {
+				db.Delete(calcBlockCommitKey(commitHeight))
+			}
+			if tuple.corruptCommitInDB {
+				db.Set(calcBlockCommitKey(commitHeight), []byte("foo-bogus"))
+			}
+			bCommit := bs.LoadBlockCommit(commitHeight)
+			return &quad{block: bBlock, seenCommit: bSeenCommit, commit: bCommit, meta: bBlockMeta}, nil
+		})
+
+		if subStr := tuple.wantPanic; subStr != "" {
+			if panicErr == nil {
+				t.Errorf("#%d: want a non-nil panic", i)
+			} else if got := panicErr.Error(); !strings.Contains(got, subStr) {
+				t.Errorf("#%d:\n\tgotErr: %q\nwant substring: %q", i, got, subStr)
+			}
+			continue
+		}
+
+		if tuple.wantErr {
+			if err == nil {
+				t.Errorf("#%d: got nil error", i)
+			}
+			continue
+		}
+
+		assert.Nil(t, panicErr, "#%d: unexpected panic", i)
+		assert.Nil(t, err, "#%d: expecting a non-nil error", i)
+		qua, ok := res.(*quad)
+		if !ok || qua == nil {
+			t.Errorf("#%d: got nil quad back; gotType=%T", i, res)
+			continue
+		}
+		if tuple.eraseSeenCommitInDB {
+			assert.Nil(t, qua.seenCommit, "erased the seenCommit in the DB hence we should get back a nil seenCommit")
+		}
+		if tuple.eraseCommitInDB {
+			assert.Nil(t, qua.commit, "erased the commit in the DB hence we should get back a nil commit")
+		}
+	}
+}
+
+func binarySerializeIt(v interface{}) []byte {
+	var n int
+	var err error
+	buf := new(bytes.Buffer)
+	wire.WriteBinary(v, buf, &n, &err)
+	return buf.Bytes()
+}
+
+func TestLoadBlockPart(t *testing.T) {
+	bs, db := freshBlockStore()
+	height, index := int64(10), 1
+	loadPart := func() (interface{}, error) {
+		part := bs.LoadBlockPart(height, index)
+		return part, nil
+	}
+
+	// Initially no contents.
+	// 1. Requesting for a non-existent block shouldn't fail
+	res, _, panicErr := doFn(loadPart)
+	require.Nil(t, panicErr, "a non-existent block part shouldn't cause a panic")
+	require.Nil(t, res, "a non-existent block part should return nil")
+
+	// 2. Next save a corrupted block then try to load it
+	db.Set(calcBlockPartKey(height, index), []byte("Tendermint"))
+	res, _, panicErr = doFn(loadPart)
+	require.NotNil(t, panicErr, "expecting a non-nil panic")
+	require.Contains(t, panicErr.Error(), "Error reading block part")
+
+	// 3. A good block serialized and saved to the DB should be retrievable
+	db.Set(calcBlockPartKey(height, index), binarySerializeIt(part1))
+	gotPart, _, panicErr := doFn(loadPart)
+	require.Nil(t, panicErr, "an existent and proper block should not panic")
+	require.Nil(t, res, "a properly saved block should return a proper block")
+	require.Equal(t, gotPart.(*types.Part).Hash(), part1.Hash(), "expecting successful retrieval of previously saved block")
+}
+
+func TestLoadBlockMeta(t *testing.T) {
+	bs, db := freshBlockStore()
+	height := int64(10)
+	loadMeta := func() (interface{}, error) {
+		meta := bs.LoadBlockMeta(height)
+		return meta, nil
+	}
+
+	// Initially no contents.
+	// 1. Requesting for a non-existent blockMeta shouldn't fail
+	res, _, panicErr := doFn(loadMeta)
+	require.Nil(t, panicErr, "a non-existent blockMeta shouldn't cause a panic")
+	require.Nil(t, res, "a non-existent blockMeta should return nil")
+
+	// 2. Next save a corrupted blockMeta then try to load it
+	db.Set(calcBlockMetaKey(height), []byte("Tendermint-Meta"))
+	res, _, panicErr = doFn(loadMeta)
+	require.NotNil(t, panicErr, "expecting a non-nil panic")
+	require.Contains(t, panicErr.Error(), "Error reading block meta")
+
+	// 3. A good blockMeta serialized and saved to the DB should be retrievable
+	meta := &types.BlockMeta{}
+	db.Set(calcBlockMetaKey(height), binarySerializeIt(meta))
+	gotMeta, _, panicErr := doFn(loadMeta)
+	require.Nil(t, panicErr, "an existent and proper block should not panic")
+	require.Nil(t, res, "a properly saved blockMeta should return a proper blocMeta ")
+	require.Equal(t, binarySerializeIt(meta), binarySerializeIt(gotMeta), "expecting successful retrieval of previously saved blockMeta")
+}
+
+func TestBlockFetchAtHeight(t *testing.T) {
+	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
+	block := makeBlock(bs.Height()+1, state)
+
+	partSet := block.MakePartSet(2)
+	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10, Timestamp: time.Now().UTC()}}}
+
+	bs.SaveBlock(block, partSet, seenCommit)
+	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
+
+	blockAtHeight := bs.LoadBlock(bs.Height())
+	require.Equal(t, block.Hash(), blockAtHeight.Hash(), "expecting a successful load of the last saved block")
+
+	blockAtHeightPlus1 := bs.LoadBlock(bs.Height() + 1)
+	require.Nil(t, blockAtHeightPlus1, "expecting an unsuccessful load of Height()+1")
+	blockAtHeightPlus2 := bs.LoadBlock(bs.Height() + 2)
+	require.Nil(t, blockAtHeightPlus2, "expecting an unsuccessful load of Height()+2")
+}
+
+func doFn(fn func() (interface{}, error)) (res interface{}, err error, panicErr error) {
+	defer func() {
+		if r := recover(); r != nil {
+			switch e := r.(type) {
+			case error:
+				panicErr = e
+			case string:
+				panicErr = fmt.Errorf("%s", e)
+			default:
+				if st, ok := r.(fmt.Stringer); ok {
+					panicErr = fmt.Errorf("%s", st)
+				} else {
+					panicErr = fmt.Errorf("%s", debug.Stack())
+				}
+			}
+		}
+	}()
+
+	res, err = fn()
+	return res, err, panicErr
+}
+
+func newBlock(hdr *types.Header, lastCommit *types.Commit) *types.Block {
+	return &types.Block{
+		Header:     hdr,
+		LastCommit: lastCommit,
+	}
+}

circle.yml

@@ -1,34 +1,34 @@
+---
 machine:
   environment:
     MACH_PREFIX: tendermint-test-mach
-    GOPATH: /home/ubuntu/.go_workspace
-    REPO: $GOPATH/src/github.com/$CIRCLE_PROJECT_USERNAME/$CIRCLE_PROJECT_REPONAME
     DOCKER_VERSION: 1.10.0
-    DOCKER_MACHINE_VERSION: 0.6.0
+    DOCKER_MACHINE_VERSION: 0.9.0
+    GOPATH: "$HOME/.go_project"
+    PROJECT_PARENT_PATH: "$GOPATH/src/github.com/$CIRCLE_PROJECT_USERNAME"
+    PROJECT_PATH: "$PROJECT_PARENT_PATH/$CIRCLE_PROJECT_REPONAME"
+    PATH: "$HOME/.go_project/bin:${PATH}"
   hosts:
-    circlehost: 127.0.0.1
     localhost: 127.0.0.1
 
-checkout:
-  post:
-    - rm -rf $REPO
-    - mkdir -p $HOME/.go_workspace/src/github.com/$CIRCLE_PROJECT_USERNAME
-    - mv $HOME/$CIRCLE_PROJECT_REPONAME $REPO
-    # - git submodule sync
-    # - git submodule update --init # use submodules
-
 dependencies:
   override:
-    - echo $MACH_PREFIX $GOPATH $REPO $DOCKER_VERSION $DOCKER_MACHINE_VERSION
     - curl -sSL https://s3.amazonaws.com/circle-downloads/install-circleci-docker.sh | sudo bash -s -- $DOCKER_VERSION
-    - sudo curl -sSL -o /usr/bin/docker-machine https://github.com/docker/machine/releases/download/v$DOCKER_MACHINE_VERSION/docker-machine-linux-x86_64; sudo chmod 0755 /usr/bin/docker-machine
     - sudo start docker
+    - sudo curl -sSL -o /usr/bin/docker-machine "https://github.com/docker/machine/releases/download/v$DOCKER_MACHINE_VERSION/docker-machine-`uname -s`-`uname -m`"; sudo chmod 0755 /usr/bin/docker-machine
+    - mkdir -p "$PROJECT_PARENT_PATH"
+    - ln -sf "$HOME/$CIRCLE_PROJECT_REPONAME/" "$PROJECT_PATH"
+  post:
     - go version
     - docker version
     - docker-machine version
 
 test:
   override:
-    - "cd $REPO && make test_integrations"
+    - cd "$PROJECT_PATH" && set -o pipefail && make test_integrations 2>&1 | tee test_integrations.log:
+        timeout: 1800
   post:
-    - bash <(curl -s https://codecov.io/bash)
+    - cd "$PROJECT_PATH" && mv test_integrations.log "${CIRCLE_ARTIFACTS}"
+    - cd "$PROJECT_PATH" && bash <(curl -s https://codecov.io/bash) -f coverage.txt
+    - cd "$PROJECT_PATH" && mv coverage.txt "${CIRCLE_ARTIFACTS}"
+    - cd "$PROJECT_PATH" && cp test/logs/messages "${CIRCLE_ARTIFACTS}/docker_logs.txt"

cmd/tendermint/commands/gen_validator.go

@@ -0,0 +1,28 @@
+package commands
+
+import (
+	"encoding/json"
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/types"
+)
+
+// GenValidatorCmd allows the generation of a keypair for a
+// validator.
+var GenValidatorCmd = &cobra.Command{
+	Use:   "gen_validator",
+	Short: "Generate new validator keypair",
+	Run:   genValidator,
+}
+
+func genValidator(cmd *cobra.Command, args []string) {
+	privValidator := types.GenPrivValidatorFS("")
+	privValidatorJSONBytes, err := json.MarshalIndent(privValidator, "", "\t")
+	if err != nil {
+		panic(err)
+	}
+	fmt.Printf(`%v
+`, string(privValidatorJSONBytes))
+}

cmd/tendermint/commands/init.go

@@ -0,0 +1,48 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+// InitFilesCmd initialises a fresh Tendermint Core instance.
+var InitFilesCmd = &cobra.Command{
+	Use:   "init",
+	Short: "Initialize Tendermint",
+	Run:   initFiles,
+}
+
+func initFiles(cmd *cobra.Command, args []string) {
+	// private validator
+	privValFile := config.PrivValidatorFile()
+	var privValidator *types.PrivValidatorFS
+	if cmn.FileExists(privValFile) {
+		privValidator = types.LoadPrivValidatorFS(privValFile)
+		logger.Info("Found private validator", "path", privValFile)
+	} else {
+		privValidator = types.GenPrivValidatorFS(privValFile)
+		privValidator.Save()
+		logger.Info("Genetated private validator", "path", privValFile)
+	}
+
+	// genesis file
+	genFile := config.GenesisFile()
+	if cmn.FileExists(genFile) {
+		logger.Info("Found genesis file", "path", genFile)
+	} else {
+		genDoc := types.GenesisDoc{
+			ChainID: cmn.Fmt("test-chain-%v", cmn.RandStr(6)),
+		}
+		genDoc.Validators = []types.GenesisValidator{{
+			PubKey: privValidator.GetPubKey(),
+			Power:  10,
+		}}
+
+		if err := genDoc.SaveAs(genFile); err != nil {
+			panic(err)
+		}
+		logger.Info("Genetated genesis file", "path", genFile)
+	}
+}

cmd/tendermint/commands/lite.go

@@ -0,0 +1,60 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/tendermint/tendermint/lite/proxy"
+	rpcclient "github.com/tendermint/tendermint/rpc/client"
+)
+
+// LiteCmd represents the base command when called without any subcommands
+var LiteCmd = &cobra.Command{
+	Use:   "lite",
+	Short: "Run lite-client proxy server, verifying tendermint rpc",
+	Long: `This node will run a secure proxy to a tendermint rpc server.
+
+All calls that can be tracked back to a block header by a proof
+will be verified before passing them back to the caller. Other that
+that it will present the same interface as a full tendermint node,
+just with added trust and running locally.`,
+	RunE:         runProxy,
+	SilenceUsage: true,
+}
+
+var (
+	listenAddr string
+	nodeAddr   string
+	chainID    string
+	home       string
+)
+
+func init() {
+	LiteCmd.Flags().StringVar(&listenAddr, "laddr", ":8888", "Serve the proxy on the given port")
+	LiteCmd.Flags().StringVar(&nodeAddr, "node", "localhost:46657", "Connect to a Tendermint node at this address")
+	LiteCmd.Flags().StringVar(&chainID, "chain-id", "tendermint", "Specify the Tendermint chain ID")
+	LiteCmd.Flags().StringVar(&home, "home-dir", ".tendermint-lite", "Specify the home directory")
+}
+
+func runProxy(cmd *cobra.Command, args []string) error {
+	// First, connect a client
+	node := rpcclient.NewHTTP(nodeAddr, "/websocket")
+
+	cert, err := proxy.GetCertifier(chainID, home, nodeAddr)
+	if err != nil {
+		return err
+	}
+	sc := proxy.SecureClient(node, cert)
+
+	err = proxy.StartProxy(sc, listenAddr, logger)
+	if err != nil {
+		return err
+	}
+
+	cmn.TrapSignal(func() {
+		// TODO: close up shop
+	})
+
+	return nil
+}

cmd/tendermint/commands/probe_upnp.go

@@ -0,0 +1,32 @@
+package commands
+
+import (
+	"encoding/json"
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/p2p/upnp"
+)
+
+// ProbeUpnpCmd adds capabilities to test the UPnP functionality.
+var ProbeUpnpCmd = &cobra.Command{
+	Use:   "probe_upnp",
+	Short: "Test UPnP functionality",
+	RunE:  probeUpnp,
+}
+
+func probeUpnp(cmd *cobra.Command, args []string) error {
+	capabilities, err := upnp.Probe(logger)
+	if err != nil {
+		fmt.Println("Probe failed: ", err)
+	} else {
+		fmt.Println("Probe success!")
+		jsonBytes, err := json.Marshal(capabilities)
+		if err != nil {
+			return err
+		}
+		fmt.Println(string(jsonBytes))
+	}
+	return nil
+}

cmd/tendermint/commands/replay.go

@@ -0,0 +1,26 @@
+package commands
+
+import (
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/consensus"
+)
+
+// ReplayCmd allows replaying of messages from the WAL.
+var ReplayCmd = &cobra.Command{
+	Use:   "replay",
+	Short: "Replay messages from WAL",
+	Run: func(cmd *cobra.Command, args []string) {
+		consensus.RunReplayFile(config.BaseConfig, config.Consensus, false)
+	},
+}
+
+// ReplayConsoleCmd allows replaying of messages from the WAL in a
+// console.
+var ReplayConsoleCmd = &cobra.Command{
+	Use:   "replay_console",
+	Short: "Replay messages from WAL in a console",
+	Run: func(cmd *cobra.Command, args []string) {
+		consensus.RunReplayFile(config.BaseConfig, config.Consensus, true)
+	},
+}

cmd/tendermint/commands/reset_priv_validator.go

@@ -0,0 +1,61 @@
+package commands
+
+import (
+	"os"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tmlibs/log"
+)
+
+// ResetAllCmd removes the database of this Tendermint core
+// instance.
+var ResetAllCmd = &cobra.Command{
+	Use:   "unsafe_reset_all",
+	Short: "(unsafe) Remove all the data and WAL, reset this node's validator",
+	Run:   resetAll,
+}
+
+// ResetPrivValidatorCmd resets the private validator files.
+var ResetPrivValidatorCmd = &cobra.Command{
+	Use:   "unsafe_reset_priv_validator",
+	Short: "(unsafe) Reset this node's validator",
+	Run:   resetPrivValidator,
+}
+
+// ResetAll removes the privValidator files.
+// Exported so other CLI tools can use it.
+func ResetAll(dbDir, privValFile string, logger log.Logger) {
+	resetPrivValidatorFS(privValFile, logger)
+	if err := os.RemoveAll(dbDir); err != nil {
+		logger.Error("Error removing directory", "err", err)
+		return
+	}
+	logger.Info("Removed all data", "dir", dbDir)
+}
+
+// XXX: this is totally unsafe.
+// it's only suitable for testnets.
+func resetAll(cmd *cobra.Command, args []string) {
+	ResetAll(config.DBDir(), config.PrivValidatorFile(), logger)
+}
+
+// XXX: this is totally unsafe.
+// it's only suitable for testnets.
+func resetPrivValidator(cmd *cobra.Command, args []string) {
+	resetPrivValidatorFS(config.PrivValidatorFile(), logger)
+}
+
+func resetPrivValidatorFS(privValFile string, logger log.Logger) {
+	// Get PrivValidator
+	if _, err := os.Stat(privValFile); err == nil {
+		privValidator := types.LoadPrivValidatorFS(privValFile)
+		privValidator.Reset()
+		logger.Info("Reset PrivValidator", "file", privValFile)
+	} else {
+		privValidator := types.GenPrivValidatorFS(privValFile)
+		privValidator.Save()
+		logger.Info("Generated PrivValidator", "file", privValFile)
+	}
+}

cmd/tendermint/commands/root.go

@@ -0,0 +1,58 @@
+package commands
+
+import (
+	"os"
+
+	"github.com/spf13/cobra"
+	"github.com/spf13/viper"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tmlibs/cli"
+	tmflags "github.com/tendermint/tmlibs/cli/flags"
+	"github.com/tendermint/tmlibs/log"
+)
+
+var (
+	config = cfg.DefaultConfig()
+	logger = log.NewTMLogger(log.NewSyncWriter(os.Stdout)).With("module", "main")
+)
+
+func init() {
+	RootCmd.PersistentFlags().String("log_level", config.LogLevel, "Log level")
+}
+
+// ParseConfig retrieves the default environment configuration,
+// sets up the Tendermint root and ensures that the root exists
+func ParseConfig() (*cfg.Config, error) {
+	conf := cfg.DefaultConfig()
+	err := viper.Unmarshal(conf)
+	if err != nil {
+		return nil, err
+	}
+	conf.SetRoot(conf.RootDir)
+	cfg.EnsureRoot(conf.RootDir)
+	return conf, err
+}
+
+// RootCmd is the root command for Tendermint core.
+var RootCmd = &cobra.Command{
+	Use:   "tendermint",
+	Short: "Tendermint Core (BFT Consensus) in Go",
+	PersistentPreRunE: func(cmd *cobra.Command, args []string) (err error) {
+		if cmd.Name() == VersionCmd.Name() {
+			return nil
+		}
+		config, err = ParseConfig()
+		if err != nil {
+			return err
+		}
+		logger, err = tmflags.ParseLogLevel(config.LogLevel, logger, cfg.DefaultLogLevel())
+		if err != nil {
+			return err
+		}
+		if viper.GetBool(cli.TraceFlag) {
+			logger = log.NewTracingLogger(logger)
+		}
+		return nil
+	},
+}

cmd/tendermint/commands/root_test.go

@@ -0,0 +1,110 @@
+package commands
+
+import (
+	"os"
+	"strconv"
+	"testing"
+
+	"github.com/spf13/cobra"
+	"github.com/spf13/viper"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tmlibs/cli"
+)
+
+var (
+	defaultRoot = os.ExpandEnv("$HOME/.some/test/dir")
+)
+
+const (
+	rootName = "root"
+)
+
+// isolate provides a clean setup and returns a copy of RootCmd you can
+// modify in the test cases.
+// NOTE: it unsets all TM* env variables.
+func isolate(cmds ...*cobra.Command) cli.Executable {
+	if err := os.Unsetenv("TMHOME"); err != nil {
+		panic(err)
+	}
+	if err := os.Unsetenv("TM_HOME"); err != nil {
+		panic(err)
+	}
+	if err := os.RemoveAll(defaultRoot); err != nil {
+		panic(err)
+	}
+
+	viper.Reset()
+	config = cfg.DefaultConfig()
+	r := &cobra.Command{
+		Use:               rootName,
+		PersistentPreRunE: RootCmd.PersistentPreRunE,
+	}
+	r.AddCommand(cmds...)
+	wr := cli.PrepareBaseCmd(r, "TM", defaultRoot)
+	return wr
+}
+
+func TestRootConfig(t *testing.T) {
+	assert, require := assert.New(t), require.New(t)
+
+	// we pre-create a config file we can refer to in the rest of
+	// the test cases.
+	cvals := map[string]string{
+		"moniker":   "monkey",
+		"fast_sync": "false",
+	}
+	// proper types of the above settings
+	cfast := false
+	conf, err := cli.WriteDemoConfig(cvals)
+	require.Nil(err)
+
+	defaults := cfg.DefaultConfig()
+	dmax := defaults.P2P.MaxNumPeers
+
+	cases := []struct {
+		args     []string
+		env      map[string]string
+		root     string
+		moniker  string
+		fastSync bool
+		maxPeer  int
+	}{
+		{nil, nil, defaultRoot, defaults.Moniker, defaults.FastSync, dmax},
+		// try multiple ways of setting root (two flags, cli vs. env)
+		{[]string{"--home", conf}, nil, conf, cvals["moniker"], cfast, dmax},
+		{nil, map[string]string{"TMHOME": conf}, conf, cvals["moniker"], cfast, dmax},
+		// check setting p2p subflags two different ways
+		{[]string{"--p2p.max_num_peers", "420"}, nil, defaultRoot, defaults.Moniker, defaults.FastSync, 420},
+		{nil, map[string]string{"TM_P2P_MAX_NUM_PEERS": "17"}, defaultRoot, defaults.Moniker, defaults.FastSync, 17},
+		// try to set env that have no flags attached...
+		{[]string{"--home", conf}, map[string]string{"TM_MONIKER": "funny"}, conf, "funny", cfast, dmax},
+	}
+
+	for idx, tc := range cases {
+		i := strconv.Itoa(idx)
+		// test command that does nothing, except trigger unmarshalling in root
+		noop := &cobra.Command{
+			Use: "noop",
+			RunE: func(cmd *cobra.Command, args []string) error {
+				return nil
+			},
+		}
+		noop.Flags().Int("p2p.max_num_peers", defaults.P2P.MaxNumPeers, "")
+		cmd := isolate(noop)
+
+		args := append([]string{rootName, noop.Use}, tc.args...)
+		err := cli.RunWithArgs(cmd, args, tc.env)
+		require.Nil(err, i)
+		assert.Equal(tc.root, config.RootDir, i)
+		assert.Equal(tc.root, config.P2P.RootDir, i)
+		assert.Equal(tc.root, config.Consensus.RootDir, i)
+		assert.Equal(tc.root, config.Mempool.RootDir, i)
+		assert.Equal(tc.moniker, config.Moniker, i)
+		assert.Equal(tc.fastSync, config.FastSync, i)
+		assert.Equal(tc.maxPeer, config.P2P.MaxNumPeers, i)
+	}
+
+}

cmd/tendermint/commands/run_node.go

@@ -0,0 +1,67 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	nm "github.com/tendermint/tendermint/node"
+)
+
+// AddNodeFlags exposes some common configuration options on the command-line
+// These are exposed for convenience of commands embedding a tendermint node
+func AddNodeFlags(cmd *cobra.Command) {
+	// bind flags
+	cmd.Flags().String("moniker", config.Moniker, "Node Name")
+
+	// node flags
+	cmd.Flags().Bool("fast_sync", config.FastSync, "Fast blockchain syncing")
+
+	// abci flags
+	cmd.Flags().String("proxy_app", config.ProxyApp, "Proxy app address, or 'nilapp' or 'dummy' for local testing.")
+	cmd.Flags().String("abci", config.ABCI, "Specify abci transport (socket | grpc)")
+
+	// rpc flags
+	cmd.Flags().String("rpc.laddr", config.RPC.ListenAddress, "RPC listen address. Port required")
+	cmd.Flags().String("rpc.grpc_laddr", config.RPC.GRPCListenAddress, "GRPC listen address (BroadcastTx only). Port required")
+	cmd.Flags().Bool("rpc.unsafe", config.RPC.Unsafe, "Enabled unsafe rpc methods")
+
+	// p2p flags
+	cmd.Flags().String("p2p.laddr", config.P2P.ListenAddress, "Node listen address. (0.0.0.0:0 means any interface, any port)")
+	cmd.Flags().String("p2p.seeds", config.P2P.Seeds, "Comma delimited host:port seed nodes")
+	cmd.Flags().Bool("p2p.skip_upnp", config.P2P.SkipUPNP, "Skip UPNP configuration")
+	cmd.Flags().Bool("p2p.pex", config.P2P.PexReactor, "Enable/disable Peer-Exchange")
+
+	// consensus flags
+	cmd.Flags().Bool("consensus.create_empty_blocks", config.Consensus.CreateEmptyBlocks, "Set this to false to only produce blocks when there are txs or when the AppHash changes")
+}
+
+// NewRunNodeCmd returns the command that allows the CLI to start a
+// node. It can be used with a custom PrivValidator and in-process ABCI application.
+func NewRunNodeCmd(nodeProvider nm.NodeProvider) *cobra.Command {
+	cmd := &cobra.Command{
+		Use:   "node",
+		Short: "Run the tendermint node",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			// Create & start node
+			n, err := nodeProvider(config, logger)
+			if err != nil {
+				return fmt.Errorf("Failed to create node: %v", err)
+			}
+
+			if err := n.Start(); err != nil {
+				return fmt.Errorf("Failed to start node: %v", err)
+			} else {
+				logger.Info("Started node", "nodeInfo", n.Switch().NodeInfo())
+			}
+
+			// Trap signal, run forever.
+			n.RunForever()
+
+			return nil
+		},
+	}
+
+	AddNodeFlags(cmd)
+	return cmd
+}

cmd/tendermint/commands/show_validator.go

@@ -0,0 +1,23 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/go-wire/data"
+	"github.com/tendermint/tendermint/types"
+)
+
+// ShowValidatorCmd adds capabilities for showing the validator info.
+var ShowValidatorCmd = &cobra.Command{
+	Use:   "show_validator",
+	Short: "Show this node's validator info",
+	Run:   showValidator,
+}
+
+func showValidator(cmd *cobra.Command, args []string) {
+	privValidator := types.LoadOrGenPrivValidatorFS(config.PrivValidatorFile())
+	pubKeyJSONBytes, _ := data.ToJSON(privValidator.PubKey)
+	fmt.Println(string(pubKeyJSONBytes))
+}

cmd/tendermint/commands/testnet.go

@@ -0,0 +1,94 @@
+package commands
+
+import (
+	"fmt"
+	"path"
+	"time"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+//flags
+var (
+	nValidators int
+	dataDir     string
+)
+
+func init() {
+	TestnetFilesCmd.Flags().IntVar(&nValidators, "n", 4,
+		"Number of validators to initialize the testnet with")
+	TestnetFilesCmd.Flags().StringVar(&dataDir, "dir", "mytestnet",
+		"Directory to store initialization data for the testnet")
+}
+
+// TestnetFilesCmd allows initialisation of files for a
+// Tendermint testnet.
+var TestnetFilesCmd = &cobra.Command{
+	Use:   "testnet",
+	Short: "Initialize files for a Tendermint testnet",
+	Run:   testnetFiles,
+}
+
+func testnetFiles(cmd *cobra.Command, args []string) {
+
+	genVals := make([]types.GenesisValidator, nValidators)
+
+	// Initialize core dir and priv_validator.json's
+	for i := 0; i < nValidators; i++ {
+		mach := cmn.Fmt("mach%d", i)
+		err := initMachCoreDirectory(dataDir, mach)
+		if err != nil {
+			cmn.Exit(err.Error())
+		}
+		// Read priv_validator.json to populate vals
+		privValFile := path.Join(dataDir, mach, "priv_validator.json")
+		privVal := types.LoadPrivValidatorFS(privValFile)
+		genVals[i] = types.GenesisValidator{
+			PubKey: privVal.GetPubKey(),
+			Power:  1,
+			Name:   mach,
+		}
+	}
+
+	// Generate genesis doc from generated validators
+	genDoc := &types.GenesisDoc{
+		GenesisTime: time.Now(),
+		ChainID:     "chain-" + cmn.RandStr(6),
+		Validators:  genVals,
+	}
+
+	// Write genesis file.
+	for i := 0; i < nValidators; i++ {
+		mach := cmn.Fmt("mach%d", i)
+		if err := genDoc.SaveAs(path.Join(dataDir, mach, "genesis.json")); err != nil {
+			panic(err)
+		}
+	}
+
+	fmt.Println(cmn.Fmt("Successfully initialized %v node directories", nValidators))
+}
+
+// Initialize per-machine core directory
+func initMachCoreDirectory(base, mach string) error {
+	dir := path.Join(base, mach)
+	err := cmn.EnsureDir(dir, 0777)
+	if err != nil {
+		return err
+	}
+
+	// Create priv_validator.json file if not present
+	ensurePrivValidator(path.Join(dir, "priv_validator.json"))
+	return nil
+
+}
+
+func ensurePrivValidator(file string) {
+	if cmn.FileExists(file) {
+		return
+	}
+	privValidator := types.GenPrivValidatorFS(file)
+	privValidator.Save()
+}

cmd/tendermint/commands/version.go

@@ -0,0 +1,18 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/version"
+)
+
+// VersionCmd ...
+var VersionCmd = &cobra.Command{
+	Use:   "version",
+	Short: "Show version info",
+	Run: func(cmd *cobra.Command, args []string) {
+		fmt.Println(version.Version)
+	},
+}

cmd/tendermint/flags.go

@@ -1,53 +0,0 @@
-package main
-
-import (
-	flag "github.com/spf13/pflag"
-	"os"
-
-	cfg "github.com/tendermint/go-config"
-)
-
-func parseFlags(config cfg.Config, args []string) {
-	var (
-		printHelp     bool
-		moniker       string
-		nodeLaddr     string
-		seeds         string
-		fastSync      bool
-		skipUPNP      bool
-		rpcLaddr      string
-		logLevel      string
-		proxyApp      string
-		tmspTransport string
-	)
-
-	// Declare flags
-	var flags = flag.NewFlagSet("main", flag.ExitOnError)
-	flags.BoolVar(&printHelp, "help", false, "Print this help message.")
-	flags.StringVar(&moniker, "moniker", config.GetString("moniker"), "Node Name")
-	flags.StringVar(&nodeLaddr, "node_laddr", config.GetString("node_laddr"), "Node listen address. (0.0.0.0:0 means any interface, any port)")
-	flags.StringVar(&seeds, "seeds", config.GetString("seeds"), "Comma delimited host:port seed nodes")
-	flags.BoolVar(&fastSync, "fast_sync", config.GetBool("fast_sync"), "Fast blockchain syncing")
-	flags.BoolVar(&skipUPNP, "skip_upnp", config.GetBool("skip_upnp"), "Skip UPNP configuration")
-	flags.StringVar(&rpcLaddr, "rpc_laddr", config.GetString("rpc_laddr"), "RPC listen address. Port required")
-	flags.StringVar(&logLevel, "log_level", config.GetString("log_level"), "Log level")
-	flags.StringVar(&proxyApp, "proxy_app", config.GetString("proxy_app"),
-		"Proxy app address, or 'nilapp' or 'dummy' for local testing.")
-	flags.StringVar(&tmspTransport, "tmsp", config.GetString("tmsp"), "Specify tmsp transport (socket | grpc)")
-	flags.Parse(args)
-	if printHelp {
-		flags.PrintDefaults()
-		os.Exit(0)
-	}
-
-	// Merge parsed flag values onto app.
-	config.Set("moniker", moniker)
-	config.Set("node_laddr", nodeLaddr)
-	config.Set("seeds", seeds)
-	config.Set("fast_sync", fastSync)
-	config.Set("skip_upnp", skipUPNP)
-	config.Set("rpc_laddr", rpcLaddr)
-	config.Set("log_level", logLevel)
-	config.Set("proxy_app", proxyApp)
-	config.Set("tmsp", tmspTransport)
-}

cmd/tendermint/gen_validator.go

@@ -1,23 +0,0 @@
-package main
-
-import (
-	"fmt"
-
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/types"
-)
-
-func gen_validator() {
-
-	privValidator := types.GenPrivValidator()
-	privValidatorJSONBytes := wire.JSONBytesPretty(privValidator)
-	fmt.Printf(`Generated a new validator!
-Paste the following JSON into your %v file
-
-%v
-
-`,
-		config.GetString("priv_validator_file"),
-		string(privValidatorJSONBytes),
-	)
-}

cmd/tendermint/init.go

@@ -1,23 +0,0 @@
-package main
-
-import (
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/tendermint/types"
-)
-
-func init_files() {
-	privValidator := types.GenPrivValidator()
-	privValidator.SetFile(config.GetString("priv_validator_file"))
-	privValidator.Save()
-
-	genDoc := types.GenesisDoc{
-		ChainID: Fmt("test-chain-%v", RandStr(6)),
-	}
-	genDoc.Validators = []types.GenesisValidator{types.GenesisValidator{
-		PubKey: privValidator.PubKey,
-		Amount: 10,
-	}}
-
-	genDoc.SaveAs(config.GetString("genesis_file"))
-
-}

cmd/tendermint/log.go

@@ -1,7 +0,0 @@
-package main
-
-import (
-	"github.com/tendermint/go-logger"
-)
-
-var log = logger.New("module", "main")

cmd/tendermint/main.go

@@ -1,66 +1,44 @@
 package main
 
 import (
-	"fmt"
 	"os"
 
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/go-logger"
-	tmcfg "github.com/tendermint/tendermint/config/tendermint"
-	"github.com/tendermint/tendermint/node"
-	"github.com/tendermint/tendermint/version"
+	"github.com/tendermint/tmlibs/cli"
+
+	cmd "github.com/tendermint/tendermint/cmd/tendermint/commands"
+	nm "github.com/tendermint/tendermint/node"
 )
 
-var config cfg.Config
-
 func main() {
+	rootCmd := cmd.RootCmd
+	rootCmd.AddCommand(
+		cmd.GenValidatorCmd,
+		cmd.InitFilesCmd,
+		cmd.ProbeUpnpCmd,
+		cmd.LiteCmd,
+		cmd.ReplayCmd,
+		cmd.ReplayConsoleCmd,
+		cmd.ResetAllCmd,
+		cmd.ResetPrivValidatorCmd,
+		cmd.ShowValidatorCmd,
+		cmd.TestnetFilesCmd,
+		cmd.VersionCmd)
 
-	args := os.Args[1:]
-	if len(args) == 0 {
-		fmt.Println(`Tendermint
+	// NOTE:
+	// Users wishing to:
+	//	* Use an external signer for their validators
+	//	* Supply an in-proc abci app
+	//	* Supply a genesis doc file from another source
+	//	* Provide their own DB implementation
+	// can copy this file and use something other than the
+	// DefaultNewNode function
+	nodeFunc := nm.DefaultNewNode
 
-Commands:
-    node            Run the tendermint node
-    show_validator  Show this node's validator info
-    gen_validator   Generate new validator keypair
-    probe_upnp      Test UPnP functionality
-    version         Show version info
-`)
-		return
-	}
+	// Create & start node
+	rootCmd.AddCommand(cmd.NewRunNodeCmd(nodeFunc))
 
-	// Get configuration
-	config = tmcfg.GetConfig("")
-	parseFlags(config, args[1:]) // Command line overrides
-
-	// set the log level
-	logger.SetLogLevel(config.GetString("log_level"))
-
-	switch args[0] {
-	case "node":
-		node.RunNode(config)
-	case "replay":
-		if len(args) > 1 && args[1] == "console" {
-			node.RunReplayConsole(config)
-		} else {
-			node.RunReplay(config)
-		}
-	case "init":
-		init_files()
-	case "show_validator":
-		show_validator()
-	case "gen_validator":
-		gen_validator()
-	case "probe_upnp":
-		probe_upnp()
-	case "unsafe_reset_all":
-		reset_all()
-	case "unsafe_reset_priv_validator":
-		reset_priv_validator()
-	case "version":
-		fmt.Println(version.Version)
-	default:
-		Exit(Fmt("Unknown command %v\n", args[0]))
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv("$HOME/.tendermint"))
+	if err := cmd.Execute(); err != nil {
+		panic(err)
 	}
 }

cmd/tendermint/probe_upnp.go

@@ -1,24 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"fmt"
-
-	"github.com/tendermint/go-p2p/upnp"
-)
-
-func probe_upnp() {
-
-	capabilities, err := upnp.Probe()
-	if err != nil {
-		fmt.Println("Probe failed: %v", err)
-	} else {
-		fmt.Println("Probe success!")
-		jsonBytes, err := json.Marshal(capabilities)
-		if err != nil {
-			panic(err)
-		}
-		fmt.Println(string(jsonBytes))
-	}
-
-}

cmd/tendermint/reset_priv_validator.go

@@ -1,33 +0,0 @@
-package main
-
-import (
-	"os"
-
-	"github.com/tendermint/tendermint/types"
-)
-
-// NOTE: this is totally unsafe.
-// it's only suitable for testnets.
-func reset_all() {
-	reset_priv_validator()
-	os.RemoveAll(config.GetString("db_dir"))
-	os.Remove(config.GetString("cswal"))
-}
-
-// NOTE: this is totally unsafe.
-// it's only suitable for testnets.
-func reset_priv_validator() {
-	// Get PrivValidator
-	var privValidator *types.PrivValidator
-	privValidatorFile := config.GetString("priv_validator_file")
-	if _, err := os.Stat(privValidatorFile); err == nil {
-		privValidator = types.LoadPrivValidator(privValidatorFile)
-		privValidator.Reset()
-		log.Notice("Reset PrivValidator", "file", privValidatorFile)
-	} else {
-		privValidator = types.GenPrivValidator()
-		privValidator.SetFile(privValidatorFile)
-		privValidator.Save()
-		log.Notice("Generated PrivValidator", "file", privValidatorFile)
-	}
-}

cmd/tendermint/show_validator.go

@@ -1,14 +0,0 @@
-package main
-
-import (
-	"fmt"
-
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/types"
-)
-
-func show_validator() {
-	privValidatorFile := config.GetString("priv_validator_file")
-	privValidator := types.LoadOrGenPrivValidator(privValidatorFile)
-	fmt.Println(string(wire.JSONBytesPretty(privValidator.PubKey)))
-}

config/config.go

@@ -0,0 +1,475 @@
+package config
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"time"
+)
+
+// Config defines the top level configuration for a Tendermint node
+type Config struct {
+	// Top level options use an anonymous struct
+	BaseConfig `mapstructure:",squash"`
+
+	// Options for services
+	RPC       *RPCConfig       `mapstructure:"rpc"`
+	P2P       *P2PConfig       `mapstructure:"p2p"`
+	Mempool   *MempoolConfig   `mapstructure:"mempool"`
+	Consensus *ConsensusConfig `mapstructure:"consensus"`
+	TxIndex   *TxIndexConfig   `mapstructure:"tx_index"`
+}
+
+// DefaultConfig returns a default configuration for a Tendermint node
+func DefaultConfig() *Config {
+	return &Config{
+		BaseConfig: DefaultBaseConfig(),
+		RPC:        DefaultRPCConfig(),
+		P2P:        DefaultP2PConfig(),
+		Mempool:    DefaultMempoolConfig(),
+		Consensus:  DefaultConsensusConfig(),
+		TxIndex:    DefaultTxIndexConfig(),
+	}
+}
+
+// TestConfig returns a configuration that can be used for testing
+func TestConfig() *Config {
+	return &Config{
+		BaseConfig: TestBaseConfig(),
+		RPC:        TestRPCConfig(),
+		P2P:        TestP2PConfig(),
+		Mempool:    DefaultMempoolConfig(),
+		Consensus:  TestConsensusConfig(),
+		TxIndex:    DefaultTxIndexConfig(),
+	}
+}
+
+// SetRoot sets the RootDir for all Config structs
+func (cfg *Config) SetRoot(root string) *Config {
+	cfg.BaseConfig.RootDir = root
+	cfg.RPC.RootDir = root
+	cfg.P2P.RootDir = root
+	cfg.Mempool.RootDir = root
+	cfg.Consensus.RootDir = root
+	return cfg
+}
+
+//-----------------------------------------------------------------------------
+// BaseConfig
+
+// BaseConfig defines the base configuration for a Tendermint node
+type BaseConfig struct {
+	// The root directory for all data.
+	// This should be set in viper so it can unmarshal into this struct
+	RootDir string `mapstructure:"home"`
+
+	// The ID of the chain to join (should be signed with every transaction and vote)
+	ChainID string `mapstructure:"chain_id"`
+
+	// A JSON file containing the initial validator set and other meta data
+	Genesis string `mapstructure:"genesis_file"`
+
+	// A JSON file containing the private key to use as a validator in the consensus protocol
+	PrivValidator string `mapstructure:"priv_validator_file"`
+
+	// A custom human readable name for this node
+	Moniker string `mapstructure:"moniker"`
+
+	// TCP or UNIX socket address of the ABCI application,
+	// or the name of an ABCI application compiled in with the Tendermint binary
+	ProxyApp string `mapstructure:"proxy_app"`
+
+	// Mechanism to connect to the ABCI application: socket | grpc
+	ABCI string `mapstructure:"abci"`
+
+	// Output level for logging
+	LogLevel string `mapstructure:"log_level"`
+
+	// TCP or UNIX socket address for the profiling server to listen on
+	ProfListenAddress string `mapstructure:"prof_laddr"`
+
+	// If this node is many blocks behind the tip of the chain, FastSync
+	// allows them to catchup quickly by downloading blocks in parallel
+	// and verifying their commits
+	FastSync bool `mapstructure:"fast_sync"`
+
+	// If true, query the ABCI app on connecting to a new peer
+	// so the app can decide if we should keep the connection or not
+	FilterPeers bool `mapstructure:"filter_peers"` // false
+
+	// Database backend: leveldb | memdb
+	DBBackend string `mapstructure:"db_backend"`
+
+	// Database directory
+	DBPath string `mapstructure:"db_dir"`
+}
+
+// DefaultBaseConfig returns a default base configuration for a Tendermint node
+func DefaultBaseConfig() BaseConfig {
+	return BaseConfig{
+		Genesis:           "genesis.json",
+		PrivValidator:     "priv_validator.json",
+		Moniker:           defaultMoniker,
+		ProxyApp:          "tcp://127.0.0.1:46658",
+		ABCI:              "socket",
+		LogLevel:          DefaultPackageLogLevels(),
+		ProfListenAddress: "",
+		FastSync:          true,
+		FilterPeers:       false,
+		DBBackend:         "leveldb",
+		DBPath:            "data",
+	}
+}
+
+// TestBaseConfig returns a base configuration for testing a Tendermint node
+func TestBaseConfig() BaseConfig {
+	conf := DefaultBaseConfig()
+	conf.ChainID = "tendermint_test"
+	conf.ProxyApp = "dummy"
+	conf.FastSync = false
+	conf.DBBackend = "memdb"
+	return conf
+}
+
+// GenesisFile returns the full path to the genesis.json file
+func (b BaseConfig) GenesisFile() string {
+	return rootify(b.Genesis, b.RootDir)
+}
+
+// PrivValidatorFile returns the full path to the priv_validator.json file
+func (b BaseConfig) PrivValidatorFile() string {
+	return rootify(b.PrivValidator, b.RootDir)
+}
+
+// DBDir returns the full path to the database directory
+func (b BaseConfig) DBDir() string {
+	return rootify(b.DBPath, b.RootDir)
+}
+
+// DefaultLogLevel returns a default log level of "error"
+func DefaultLogLevel() string {
+	return "error"
+}
+
+// DefaultPackageLogLevels returns a default log level setting so all packages log at "error", while the `state` package logs at "info"
+func DefaultPackageLogLevels() string {
+	return fmt.Sprintf("state:info,*:%s", DefaultLogLevel())
+}
+
+//-----------------------------------------------------------------------------
+// RPCConfig
+
+// RPCConfig defines the configuration options for the Tendermint RPC server
+type RPCConfig struct {
+	RootDir string `mapstructure:"home"`
+
+	// TCP or UNIX socket address for the RPC server to listen on
+	ListenAddress string `mapstructure:"laddr"`
+
+	// TCP or UNIX socket address for the gRPC server to listen on
+	// NOTE: This server only supports /broadcast_tx_commit
+	GRPCListenAddress string `mapstructure:"grpc_laddr"`
+
+	// Activate unsafe RPC commands like /dial_seeds and /unsafe_flush_mempool
+	Unsafe bool `mapstructure:"unsafe"`
+}
+
+// DefaultRPCConfig returns a default configuration for the RPC server
+func DefaultRPCConfig() *RPCConfig {
+	return &RPCConfig{
+		ListenAddress:     "tcp://0.0.0.0:46657",
+		GRPCListenAddress: "",
+		Unsafe:            false,
+	}
+}
+
+// TestRPCConfig returns a configuration for testing the RPC server
+func TestRPCConfig() *RPCConfig {
+	conf := DefaultRPCConfig()
+	conf.ListenAddress = "tcp://0.0.0.0:36657"
+	conf.GRPCListenAddress = "tcp://0.0.0.0:36658"
+	conf.Unsafe = true
+	return conf
+}
+
+//-----------------------------------------------------------------------------
+// P2PConfig
+
+// P2PConfig defines the configuration options for the Tendermint peer-to-peer networking layer
+type P2PConfig struct {
+	RootDir string `mapstructure:"home"`
+
+	// Address to listen for incoming connections
+	ListenAddress string `mapstructure:"laddr"`
+
+	// Comma separated list of seed nodes to connect to
+	Seeds string `mapstructure:"seeds"`
+
+	// Skip UPNP port forwarding
+	SkipUPNP bool `mapstructure:"skip_upnp"`
+
+	// Path to address book
+	AddrBook string `mapstructure:"addr_book_file"`
+
+	// Set true for strict address routability rules
+	AddrBookStrict bool `mapstructure:"addr_book_strict"`
+
+	// Set true to enable the peer-exchange reactor
+	PexReactor bool `mapstructure:"pex"`
+
+	// Maximum number of peers to connect to
+	MaxNumPeers int `mapstructure:"max_num_peers"`
+
+	// Time to wait before flushing messages out on the connection, in ms
+	FlushThrottleTimeout int `mapstructure:"flush_throttle_timeout"`
+
+	// Maximum size of a message packet payload, in bytes
+	MaxMsgPacketPayloadSize int `mapstructure:"max_msg_packet_payload_size"`
+
+	// Rate at which packets can be sent, in bytes/second
+	SendRate int64 `mapstructure:"send_rate"`
+
+	// Rate at which packets can be received, in bytes/second
+	RecvRate int64 `mapstructure:"recv_rate"`
+}
+
+// DefaultP2PConfig returns a default configuration for the peer-to-peer layer
+func DefaultP2PConfig() *P2PConfig {
+	return &P2PConfig{
+		ListenAddress:           "tcp://0.0.0.0:46656",
+		AddrBook:                "addrbook.json",
+		AddrBookStrict:          true,
+		MaxNumPeers:             50,
+		FlushThrottleTimeout:    100,
+		MaxMsgPacketPayloadSize: 1024,   // 1 kB
+		SendRate:                512000, // 500 kB/s
+		RecvRate:                512000, // 500 kB/s
+		PexReactor:              true,
+	}
+}
+
+// TestP2PConfig returns a configuration for testing the peer-to-peer layer
+func TestP2PConfig() *P2PConfig {
+	conf := DefaultP2PConfig()
+	conf.ListenAddress = "tcp://0.0.0.0:36656"
+	conf.SkipUPNP = true
+	return conf
+}
+
+// AddrBookFile returns the full path to the address book
+func (p *P2PConfig) AddrBookFile() string {
+	return rootify(p.AddrBook, p.RootDir)
+}
+
+//-----------------------------------------------------------------------------
+// MempoolConfig
+
+// MempoolConfig defines the configuration options for the Tendermint mempool
+type MempoolConfig struct {
+	RootDir      string `mapstructure:"home"`
+	Recheck      bool   `mapstructure:"recheck"`
+	RecheckEmpty bool   `mapstructure:"recheck_empty"`
+	Broadcast    bool   `mapstructure:"broadcast"`
+	WalPath      string `mapstructure:"wal_dir"`
+}
+
+// DefaultMempoolConfig returns a default configuration for the Tendermint mempool
+func DefaultMempoolConfig() *MempoolConfig {
+	return &MempoolConfig{
+		Recheck:      true,
+		RecheckEmpty: true,
+		Broadcast:    true,
+		WalPath:      "data/mempool.wal",
+	}
+}
+
+// WalDir returns the full path to the mempool's write-ahead log
+func (m *MempoolConfig) WalDir() string {
+	return rootify(m.WalPath, m.RootDir)
+}
+
+//-----------------------------------------------------------------------------
+// ConsensusConfig
+
+// ConsensusConfig defines the confuguration for the Tendermint consensus service,
+// including timeouts and details about the WAL and the block structure.
+type ConsensusConfig struct {
+	RootDir  string `mapstructure:"home"`
+	WalPath  string `mapstructure:"wal_file"`
+	WalLight bool   `mapstructure:"wal_light"`
+	walFile  string // overrides WalPath if set
+
+	// All timeouts are in ms
+	TimeoutPropose        int `mapstructure:"timeout_propose"`
+	TimeoutProposeDelta   int `mapstructure:"timeout_propose_delta"`
+	TimeoutPrevote        int `mapstructure:"timeout_prevote"`
+	TimeoutPrevoteDelta   int `mapstructure:"timeout_prevote_delta"`
+	TimeoutPrecommit      int `mapstructure:"timeout_precommit"`
+	TimeoutPrecommitDelta int `mapstructure:"timeout_precommit_delta"`
+	TimeoutCommit         int `mapstructure:"timeout_commit"`
+
+	// Make progress as soon as we have all the precommits (as if TimeoutCommit = 0)
+	SkipTimeoutCommit bool `mapstructure:"skip_timeout_commit"`
+
+	// BlockSize
+	MaxBlockSizeTxs   int `mapstructure:"max_block_size_txs"`
+	MaxBlockSizeBytes int `mapstructure:"max_block_size_bytes"`
+
+	// EmptyBlocks mode and possible interval between empty blocks in seconds
+	CreateEmptyBlocks         bool `mapstructure:"create_empty_blocks"`
+	CreateEmptyBlocksInterval int  `mapstructure:"create_empty_blocks_interval"`
+
+	// Reactor sleep duration parameters are in ms
+	PeerGossipSleepDuration     int `mapstructure:"peer_gossip_sleep_duration"`
+	PeerQueryMaj23SleepDuration int `mapstructure:"peer_query_maj23_sleep_duration"`
+}
+
+// WaitForTxs returns true if the consensus should wait for transactions before entering the propose step
+func (cfg *ConsensusConfig) WaitForTxs() bool {
+	return !cfg.CreateEmptyBlocks || cfg.CreateEmptyBlocksInterval > 0
+}
+
+// EmptyBlocks returns the amount of time to wait before proposing an empty block or starting the propose timer if there are no txs available
+func (cfg *ConsensusConfig) EmptyBlocksInterval() time.Duration {
+	return time.Duration(cfg.CreateEmptyBlocksInterval) * time.Second
+}
+
+// Propose returns the amount of time to wait for a proposal
+func (cfg *ConsensusConfig) Propose(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPropose+cfg.TimeoutProposeDelta*round) * time.Millisecond
+}
+
+// Prevote returns the amount of time to wait for straggler votes after receiving any +2/3 prevotes
+func (cfg *ConsensusConfig) Prevote(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPrevote+cfg.TimeoutPrevoteDelta*round) * time.Millisecond
+}
+
+// Precommit returns the amount of time to wait for straggler votes after receiving any +2/3 precommits
+func (cfg *ConsensusConfig) Precommit(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPrecommit+cfg.TimeoutPrecommitDelta*round) * time.Millisecond
+}
+
+// Commit returns the amount of time to wait for straggler votes after receiving +2/3 precommits for a single block (ie. a commit).
+func (cfg *ConsensusConfig) Commit(t time.Time) time.Time {
+	return t.Add(time.Duration(cfg.TimeoutCommit) * time.Millisecond)
+}
+
+// PeerGossipSleep returns the amount of time to sleep if there is nothing to send from the ConsensusReactor
+func (cfg *ConsensusConfig) PeerGossipSleep() time.Duration {
+	return time.Duration(cfg.PeerGossipSleepDuration) * time.Millisecond
+}
+
+// PeerQueryMaj23Sleep returns the amount of time to sleep after each VoteSetMaj23Message is sent in the ConsensusReactor
+func (cfg *ConsensusConfig) PeerQueryMaj23Sleep() time.Duration {
+	return time.Duration(cfg.PeerQueryMaj23SleepDuration) * time.Millisecond
+}
+
+// DefaultConsensusConfig returns a default configuration for the consensus service
+func DefaultConsensusConfig() *ConsensusConfig {
+	return &ConsensusConfig{
+		WalPath:                     "data/cs.wal/wal",
+		WalLight:                    false,
+		TimeoutPropose:              3000,
+		TimeoutProposeDelta:         500,
+		TimeoutPrevote:              1000,
+		TimeoutPrevoteDelta:         500,
+		TimeoutPrecommit:            1000,
+		TimeoutPrecommitDelta:       500,
+		TimeoutCommit:               1000,
+		SkipTimeoutCommit:           false,
+		MaxBlockSizeTxs:             10000,
+		MaxBlockSizeBytes:           1, // TODO
+		CreateEmptyBlocks:           true,
+		CreateEmptyBlocksInterval:   0,
+		PeerGossipSleepDuration:     100,
+		PeerQueryMaj23SleepDuration: 2000,
+	}
+}
+
+// TestConsensusConfig returns a configuration for testing the consensus service
+func TestConsensusConfig() *ConsensusConfig {
+	config := DefaultConsensusConfig()
+	config.TimeoutPropose = 100
+	config.TimeoutProposeDelta = 1
+	config.TimeoutPrevote = 10
+	config.TimeoutPrevoteDelta = 1
+	config.TimeoutPrecommit = 10
+	config.TimeoutPrecommitDelta = 1
+	config.TimeoutCommit = 10
+	config.SkipTimeoutCommit = true
+	return config
+}
+
+// WalFile returns the full path to the write-ahead log file
+func (c *ConsensusConfig) WalFile() string {
+	if c.walFile != "" {
+		return c.walFile
+	}
+	return rootify(c.WalPath, c.RootDir)
+}
+
+// SetWalFile sets the path to the write-ahead log file
+func (c *ConsensusConfig) SetWalFile(walFile string) {
+	c.walFile = walFile
+}
+
+//-----------------------------------------------------------------------------
+// TxIndexConfig
+
+// TxIndexConfig defines the confuguration for the transaction
+// indexer, including tags to index.
+type TxIndexConfig struct {
+	// What indexer to use for transactions
+	//
+	// Options:
+	//   1) "null" (default)
+	//   2) "kv" - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
+	Indexer string `mapstructure:"indexer"`
+
+	// Comma-separated list of tags to index (by default the only tag is tx hash)
+	//
+	// It's recommended to index only a subset of tags due to possible memory
+	// bloat. This is, of course, depends on the indexer's DB and the volume of
+	// transactions.
+	IndexTags string `mapstructure:"index_tags"`
+
+	// When set to true, tells indexer to index all tags. Note this may be not
+	// desirable (see the comment above). IndexTags has a precedence over
+	// IndexAllTags (i.e. when given both, IndexTags will be indexed).
+	IndexAllTags bool `mapstructure:"index_all_tags"`
+}
+
+// DefaultTxIndexConfig returns a default configuration for the transaction indexer.
+func DefaultTxIndexConfig() *TxIndexConfig {
+	return &TxIndexConfig{
+		Indexer:      "kv",
+		IndexTags:    "",
+		IndexAllTags: false,
+	}
+}
+
+//-----------------------------------------------------------------------------
+// Utils
+
+// helper function to make config creation independent of root dir
+func rootify(path, root string) string {
+	if filepath.IsAbs(path) {
+		return path
+	}
+	return filepath.Join(root, path)
+}
+
+//-----------------------------------------------------------------------------
+// Moniker
+
+var defaultMoniker = getDefaultMoniker()
+
+// getDefaultMoniker returns a default moniker, which is the host name. If runtime
+// fails to get the host name, "anonymous" will be returned.
+func getDefaultMoniker() string {
+	moniker, err := os.Hostname()
+	if err != nil {
+		moniker = "anonymous"
+	}
+	return moniker
+}

config/config_test.go

@@ -0,0 +1,28 @@
+package config
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestDefaultConfig(t *testing.T) {
+	assert := assert.New(t)
+
+	// set up some defaults
+	cfg := DefaultConfig()
+	assert.NotNil(cfg.P2P)
+	assert.NotNil(cfg.Mempool)
+	assert.NotNil(cfg.Consensus)
+
+	// check the root dir stuff...
+	cfg.SetRoot("/foo")
+	cfg.Genesis = "bar"
+	cfg.DBPath = "/opt/data"
+	cfg.Mempool.WalPath = "wal/mem/"
+
+	assert.Equal("/foo/bar", cfg.GenesisFile())
+	assert.Equal("/opt/data", cfg.DBDir())
+	assert.Equal("/foo/wal/mem", cfg.Mempool.WalDir())
+
+}

config/tendermint/config.go

@@ -1,107 +0,0 @@
-package tendermint
-
-import (
-	"os"
-	"path"
-	"strings"
-
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-)
-
-func getTMRoot(rootDir string) string {
-	if rootDir == "" {
-		rootDir = os.Getenv("TMROOT")
-	}
-	if rootDir == "" {
-		rootDir = os.Getenv("HOME") + "/.tendermint"
-	}
-	return rootDir
-}
-
-func initTMRoot(rootDir string) {
-	rootDir = getTMRoot(rootDir)
-	EnsureDir(rootDir, 0700)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-
-	// Write default config file if missing.
-	if !FileExists(configFilePath) {
-		// Ask user for moniker
-		// moniker := cfg.Prompt("Type hostname: ", "anonymous")
-		MustWriteFile(configFilePath, []byte(defaultConfig("anonymous")), 0644)
-	}
-}
-
-func GetConfig(rootDir string) cfg.Config {
-	rootDir = getTMRoot(rootDir)
-	initTMRoot(rootDir)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	mapConfig, err := cfg.ReadMapConfigFromFile(configFilePath)
-	if err != nil {
-		Exit(Fmt("Could not read config: %v", err))
-	}
-
-	// Set defaults or panic
-	if mapConfig.IsSet("chain_id") {
-		Exit("Cannot set 'chain_id' via config.toml")
-	}
-	if mapConfig.IsSet("revision_file") {
-		Exit("Cannot set 'revision_file' via config.toml. It must match what's in the Makefile")
-	}
-	mapConfig.SetRequired("chain_id") // blows up if you try to use it before setting.
-	mapConfig.SetDefault("genesis_file", rootDir+"/genesis.json")
-	mapConfig.SetDefault("proxy_app", "tcp://127.0.0.1:46658")
-	mapConfig.SetDefault("tmsp", "socket")
-	mapConfig.SetDefault("moniker", "anonymous")
-	mapConfig.SetDefault("node_laddr", "tcp://0.0.0.0:46656")
-	mapConfig.SetDefault("seeds", "")
-	// mapConfig.SetDefault("seeds", "goldenalchemist.chaintest.net:46656")
-	mapConfig.SetDefault("fast_sync", true)
-	mapConfig.SetDefault("skip_upnp", false)
-	mapConfig.SetDefault("addrbook_file", rootDir+"/addrbook.json")
-	mapConfig.SetDefault("priv_validator_file", rootDir+"/priv_validator.json")
-	mapConfig.SetDefault("db_backend", "leveldb")
-	mapConfig.SetDefault("db_dir", rootDir+"/data")
-	mapConfig.SetDefault("log_level", "info")
-	mapConfig.SetDefault("rpc_laddr", "tcp://0.0.0.0:46657")
-	mapConfig.SetDefault("prof_laddr", "")
-	mapConfig.SetDefault("revision_file", rootDir+"/revision")
-	mapConfig.SetDefault("cswal", rootDir+"/data/cswal")
-	mapConfig.SetDefault("cswal_light", false)
-	mapConfig.SetDefault("filter_peers", false)
-
-	mapConfig.SetDefault("block_size", 10000)
-	mapConfig.SetDefault("disable_data_hash", false)
-	mapConfig.SetDefault("timeout_propose", 3000)
-	mapConfig.SetDefault("timeout_propose_delta", 500)
-	mapConfig.SetDefault("timeout_prevote", 1000)
-	mapConfig.SetDefault("timeout_prevote_delta", 500)
-	mapConfig.SetDefault("timeout_precommit", 1000)
-	mapConfig.SetDefault("timeout_precommit_delta", 500)
-	mapConfig.SetDefault("timeout_commit", 1000)
-	mapConfig.SetDefault("mempool_recheck", true)
-	mapConfig.SetDefault("mempool_recheck_empty", true)
-	mapConfig.SetDefault("mempool_broadcast", true)
-
-	return mapConfig
-}
-
-var defaultConfigTmpl = `# This is a TOML config file.
-# For more information, see https://github.com/toml-lang/toml
-
-proxy_app = "tcp://127.0.0.1:46658"
-moniker = "__MONIKER__"
-node_laddr = "tcp://0.0.0.0:46656"
-seeds = ""
-fast_sync = true
-db_backend = "leveldb"
-log_level = "notice"
-rpc_laddr = "tcp://0.0.0.0:46657"
-`
-
-func defaultConfig(moniker string) (defaultConfig string) {
-	defaultConfig = strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
-	return
-}

config/tendermint/logrotate.config

@@ -1,22 +0,0 @@
-// If you wanted to use logrotate, I suppose this might be the config you want.
-// Instead, I'll just write our own, that way we don't need sudo to install.
-
-$HOME/.tendermint/logs/tendermint.log {
-  missingok
-  notifempty
-  rotate 12
-  daily
-  size 10M
-  compress
-  delaycompress
-}
-
-$HOME/.barak/logs/barak.log {
-  missingok
-  notifempty
-  rotate 12
-  weekly
-  size 10M
-  compress
-  delaycompress
-}

config/tendermint_test/config.go

@@ -1,151 +0,0 @@
-// Import this in all *_test.go files to initialize ~/.tendermint_test.
-
-package tendermint_test
-
-import (
-	"os"
-	"path"
-	"strings"
-
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-)
-
-func init() {
-	// Creates ~/.tendermint_test
-	EnsureDir(os.Getenv("HOME")+"/.tendermint_test", 0700)
-}
-
-func initTMRoot(rootDir string) {
-	// Remove ~/.tendermint_test_bak
-	if FileExists(rootDir + "_bak") {
-		err := os.RemoveAll(rootDir + "_bak")
-		if err != nil {
-			PanicSanity(err.Error())
-		}
-	}
-	// Move ~/.tendermint_test to ~/.tendermint_test_bak
-	if FileExists(rootDir) {
-		err := os.Rename(rootDir, rootDir+"_bak")
-		if err != nil {
-			PanicSanity(err.Error())
-		}
-	}
-	// Create new dir
-	EnsureDir(rootDir, 0700)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	genesisFilePath := path.Join(rootDir, "genesis.json")
-	privFilePath := path.Join(rootDir, "priv_validator.json")
-
-	// Write default config file if missing.
-	if !FileExists(configFilePath) {
-		// Ask user for moniker
-		// moniker := cfg.Prompt("Type hostname: ", "anonymous")
-		MustWriteFile(configFilePath, []byte(defaultConfig("anonymous")), 0644)
-	}
-	if !FileExists(genesisFilePath) {
-		MustWriteFile(genesisFilePath, []byte(defaultGenesis), 0644)
-	}
-	// we always overwrite the priv val
-	MustWriteFile(privFilePath, []byte(defaultPrivValidator), 0644)
-}
-
-func ResetConfig(localPath string) cfg.Config {
-	rootDir := os.Getenv("HOME") + "/.tendermint_test/" + localPath
-	initTMRoot(rootDir)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	mapConfig, err := cfg.ReadMapConfigFromFile(configFilePath)
-	if err != nil {
-		Exit(Fmt("Could not read config: %v", err))
-	}
-
-	// Set defaults or panic
-	if mapConfig.IsSet("chain_id") {
-		Exit("Cannot set 'chain_id' via config.toml")
-	}
-	mapConfig.SetDefault("chain_id", "tendermint_test")
-	mapConfig.SetDefault("genesis_file", rootDir+"/genesis.json")
-	mapConfig.SetDefault("proxy_app", "dummy")
-	mapConfig.SetDefault("tmsp", "socket")
-	mapConfig.SetDefault("moniker", "anonymous")
-	mapConfig.SetDefault("node_laddr", "tcp://0.0.0.0:36656")
-	mapConfig.SetDefault("fast_sync", false)
-	mapConfig.SetDefault("skip_upnp", true)
-	mapConfig.SetDefault("addrbook_file", rootDir+"/addrbook.json")
-	mapConfig.SetDefault("priv_validator_file", rootDir+"/priv_validator.json")
-	mapConfig.SetDefault("db_backend", "memdb")
-	mapConfig.SetDefault("db_dir", rootDir+"/data")
-	mapConfig.SetDefault("log_level", "debug")
-	mapConfig.SetDefault("rpc_laddr", "tcp://0.0.0.0:36657")
-	mapConfig.SetDefault("prof_laddr", "")
-	mapConfig.SetDefault("revision_file", rootDir+"/revision")
-	mapConfig.SetDefault("cswal", rootDir+"/data/cswal")
-	mapConfig.SetDefault("cswal_light", false)
-	mapConfig.SetDefault("filter_peers", false)
-
-	mapConfig.SetDefault("block_size", 10000)
-	mapConfig.SetDefault("disable_data_hash", false)
-	mapConfig.SetDefault("timeout_propose", 2000)
-	mapConfig.SetDefault("timeout_propose_delta", 500)
-	mapConfig.SetDefault("timeout_prevote", 1000)
-	mapConfig.SetDefault("timeout_prevote_delta", 500)
-	mapConfig.SetDefault("timeout_precommit", 1000)
-	mapConfig.SetDefault("timeout_precommit_delta", 500)
-	mapConfig.SetDefault("timeout_commit", 100)
-	mapConfig.SetDefault("mempool_recheck", true)
-	mapConfig.SetDefault("mempool_recheck_empty", true)
-	mapConfig.SetDefault("mempool_broadcast", true)
-
-	return mapConfig
-}
-
-var defaultConfigTmpl = `# This is a TOML config file.
-# For more information, see https://github.com/toml-lang/toml
-
-proxy_app = "dummy"
-moniker = "__MONIKER__"
-node_laddr = "tcp://0.0.0.0:36656"
-seeds = ""
-fast_sync = false
-db_backend = "memdb"
-log_level = "debug"
-rpc_laddr = "tcp://0.0.0.0:36657"
-`
-
-func defaultConfig(moniker string) (defaultConfig string) {
-	defaultConfig = strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
-	return
-}
-
-var defaultGenesis = `{
-  "genesis_time": "0001-01-01T00:00:00.000Z",
-  "chain_id": "tendermint_test",
-  "validators": [
-    {
-      "pub_key": [
-        1,
-        "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-      ],
-      "amount": 10,
-      "name": ""
-    }
-  ],
-  "app_hash": ""
-}`
-
-var defaultPrivValidator = `{
-  "address": "D028C9981F7A87F3093672BF0D5B0E2A1B3ED456",
-  "pub_key": [
-    1,
-    "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-  ],
-  "priv_key": [
-    1,
-    "27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-  ],
-  "last_height": 0,
-  "last_round": 0,
-  "last_step": 0
-}`

config/toml.go

@@ -0,0 +1,145 @@
+package config
+
+import (
+	"os"
+	"path"
+	"path/filepath"
+	"strings"
+
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+/****** these are for production settings ***********/
+
+func EnsureRoot(rootDir string) {
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(rootDir+"/data", 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+
+	configFilePath := path.Join(rootDir, "config.toml")
+
+	// Write default config file if missing.
+	if !cmn.FileExists(configFilePath) {
+		cmn.MustWriteFile(configFilePath, []byte(defaultConfig(defaultMoniker)), 0644)
+	}
+}
+
+var defaultConfigTmpl = `# This is a TOML config file.
+# For more information, see https://github.com/toml-lang/toml
+
+proxy_app = "tcp://127.0.0.1:46658"
+moniker = "__MONIKER__"
+fast_sync = true
+db_backend = "leveldb"
+log_level = "state:info,*:error"
+
+[rpc]
+laddr = "tcp://0.0.0.0:46657"
+
+[p2p]
+laddr = "tcp://0.0.0.0:46656"
+seeds = ""
+`
+
+func defaultConfig(moniker string) string {
+	return strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
+}
+
+/****** these are for test settings ***********/
+
+func ResetTestRoot(testName string) *Config {
+	rootDir := os.ExpandEnv("$HOME/.tendermint_test")
+	rootDir = filepath.Join(rootDir, testName)
+	// Remove ~/.tendermint_test_bak
+	if cmn.FileExists(rootDir + "_bak") {
+		if err := os.RemoveAll(rootDir + "_bak"); err != nil {
+			cmn.PanicSanity(err.Error())
+		}
+	}
+	// Move ~/.tendermint_test to ~/.tendermint_test_bak
+	if cmn.FileExists(rootDir) {
+		if err := os.Rename(rootDir, rootDir+"_bak"); err != nil {
+			cmn.PanicSanity(err.Error())
+		}
+	}
+	// Create new dir
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(rootDir+"/data", 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+
+	configFilePath := path.Join(rootDir, "config.toml")
+	genesisFilePath := path.Join(rootDir, "genesis.json")
+	privFilePath := path.Join(rootDir, "priv_validator.json")
+
+	// Write default config file if missing.
+	if !cmn.FileExists(configFilePath) {
+		cmn.MustWriteFile(configFilePath, []byte(testConfig(defaultMoniker)), 0644)
+	}
+	if !cmn.FileExists(genesisFilePath) {
+		cmn.MustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
+	}
+	// we always overwrite the priv val
+	cmn.MustWriteFile(privFilePath, []byte(testPrivValidator), 0644)
+
+	config := TestConfig().SetRoot(rootDir)
+	return config
+}
+
+var testConfigTmpl = `# This is a TOML config file.
+# For more information, see https://github.com/toml-lang/toml
+
+proxy_app = "dummy"
+moniker = "__MONIKER__"
+fast_sync = false
+db_backend = "memdb"
+log_level = "info"
+
+[rpc]
+laddr = "tcp://0.0.0.0:36657"
+
+[p2p]
+laddr = "tcp://0.0.0.0:36656"
+seeds = ""
+`
+
+func testConfig(moniker string) (testConfig string) {
+	testConfig = strings.Replace(testConfigTmpl, "__MONIKER__", moniker, -1)
+	return
+}
+
+var testGenesis = `{
+  "genesis_time": "0001-01-01T00:00:00.000Z",
+  "chain_id": "tendermint_test",
+  "validators": [
+    {
+      "pub_key": {
+        "type": "ed25519",
+        "data":"3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+      },
+      "power": 10,
+      "name": ""
+    }
+  ],
+  "app_hash": ""
+}`
+
+var testPrivValidator = `{
+  "address": "D028C9981F7A87F3093672BF0D5B0E2A1B3ED456",
+  "pub_key": {
+    "type": "ed25519",
+    "data": "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+  },
+  "priv_key": {
+    "type": "ed25519",
+    "data": "27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+  },
+  "last_height": 0,
+  "last_round": 0,
+  "last_step": 0
+}`

config/toml_test.go

@@ -0,0 +1,57 @@
+package config
+
+import (
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func ensureFiles(t *testing.T, rootDir string, files ...string) {
+	for _, f := range files {
+		p := rootify(rootDir, f)
+		_, err := os.Stat(p)
+		assert.Nil(t, err, p)
+	}
+}
+
+func TestEnsureRoot(t *testing.T) {
+	assert, require := assert.New(t), require.New(t)
+
+	// setup temp dir for test
+	tmpDir, err := ioutil.TempDir("", "config-test")
+	require.Nil(err)
+	defer os.RemoveAll(tmpDir) // nolint: errcheck
+
+	// create root dir
+	EnsureRoot(tmpDir)
+
+	// make sure config is set properly
+	data, err := ioutil.ReadFile(filepath.Join(tmpDir, "config.toml"))
+	require.Nil(err)
+	assert.Equal([]byte(defaultConfig(defaultMoniker)), data)
+
+	ensureFiles(t, tmpDir, "data")
+}
+
+func TestEnsureTestRoot(t *testing.T) {
+	assert, require := assert.New(t), require.New(t)
+
+	testName := "ensureTestRoot"
+
+	// create root dir
+	cfg := ResetTestRoot(testName)
+	rootDir := cfg.RootDir
+
+	// make sure config is set properly
+	data, err := ioutil.ReadFile(filepath.Join(rootDir, "config.toml"))
+	require.Nil(err)
+	assert.Equal([]byte(testConfig(defaultMoniker)), data)
+
+	// TODO: make sure the cfg returned and testconfig are the same!
+
+	ensureFiles(t, rootDir, "data", "genesis.json", "priv_validator.json")
+}

consensus/byzantine_test.go

@@ -0,0 +1,307 @@
+package consensus
+
+import (
+	"context"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	crypto "github.com/tendermint/go-crypto"
+	data "github.com/tendermint/go-wire/data"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+func init() {
+	config = ResetConfig("consensus_byzantine_test")
+}
+
+//----------------------------------------------
+// byzantine failures
+
+// 4 validators. 1 is byzantine. The other three are partitioned into A (1 val) and B (2 vals).
+// byzantine validator sends conflicting proposals into A and B,
+// and prevotes/precommits on both of them.
+// B sees a commit, A doesn't.
+// Byzantine validator refuses to prevote.
+// Heal partition and ensure A sees the commit
+func TestByzantine(t *testing.T) {
+	N := 4
+	logger := consensusLogger()
+	css := randConsensusNet(N, "consensus_byzantine_test", newMockTickerFunc(false), newCounter)
+
+	// give the byzantine validator a normal ticker
+	css[0].SetTimeoutTicker(NewTimeoutTicker())
+
+	switches := make([]*p2p.Switch, N)
+	p2pLogger := logger.With("module", "p2p")
+	for i := 0; i < N; i++ {
+		switches[i] = p2p.NewSwitch(config.P2P)
+		switches[i].SetLogger(p2pLogger.With("validator", i))
+	}
+
+	eventChans := make([]chan interface{}, N)
+	reactors := make([]p2p.Reactor, N)
+	for i := 0; i < N; i++ {
+		if i == 0 {
+			css[i].privValidator = NewByzantinePrivValidator(css[i].privValidator)
+			// make byzantine
+			css[i].decideProposal = func(j int) func(int64, int) {
+				return func(height int64, round int) {
+					byzantineDecideProposalFunc(t, height, round, css[j], switches[j])
+				}
+			}(i)
+			css[i].doPrevote = func(height int64, round int) {}
+		}
+
+		eventBus := types.NewEventBus()
+		eventBus.SetLogger(logger.With("module", "events", "validator", i))
+		err := eventBus.Start()
+		require.NoError(t, err)
+		defer eventBus.Stop()
+
+		eventChans[i] = make(chan interface{}, 1)
+		err = eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
+
+		conR := NewConsensusReactor(css[i], true) // so we dont start the consensus states
+		conR.SetLogger(logger.With("validator", i))
+		conR.SetEventBus(eventBus)
+
+		var conRI p2p.Reactor // nolint: gotype, gosimple
+		conRI = conR
+
+		if i == 0 {
+			conRI = NewByzantineReactor(conR)
+		}
+		reactors[i] = conRI
+	}
+
+	defer func() {
+		for _, r := range reactors {
+			if rr, ok := r.(*ByzantineReactor); ok {
+				rr.reactor.Switch.Stop()
+			} else {
+				r.(*ConsensusReactor).Switch.Stop()
+			}
+		}
+	}()
+
+	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
+		// ignore new switch s, we already made ours
+		switches[i].AddReactor("CONSENSUS", reactors[i])
+		return switches[i]
+	}, func(sws []*p2p.Switch, i, j int) {
+		// the network starts partitioned with globally active adversary
+		if i != 0 {
+			return
+		}
+		p2p.Connect2Switches(sws, i, j)
+	})
+
+	// start the state machines
+	byzR := reactors[0].(*ByzantineReactor)
+	s := byzR.reactor.conS.GetState()
+	byzR.reactor.SwitchToConsensus(s, 0)
+	for i := 1; i < N; i++ {
+		cr := reactors[i].(*ConsensusReactor)
+		cr.SwitchToConsensus(cr.conS.GetState(), 0)
+	}
+
+	// byz proposer sends one block to peers[0]
+	// and the other block to peers[1] and peers[2].
+	// note peers and switches order don't match.
+	peers := switches[0].Peers().List()
+	ind0 := getSwitchIndex(switches, peers[0])
+	ind1 := getSwitchIndex(switches, peers[1])
+	ind2 := getSwitchIndex(switches, peers[2])
+
+	// connect the 2 peers in the larger partition
+	p2p.Connect2Switches(switches, ind1, ind2)
+
+	// wait for someone in the big partition to make a block
+	<-eventChans[ind2]
+
+	t.Log("A block has been committed. Healing partition")
+
+	// connect the partitions
+	p2p.Connect2Switches(switches, ind0, ind1)
+	p2p.Connect2Switches(switches, ind0, ind2)
+
+	// wait till everyone makes the first new block
+	// (one of them already has)
+	wg := new(sync.WaitGroup)
+	wg.Add(2)
+	for i := 1; i < N-1; i++ {
+		go func(j int) {
+			<-eventChans[j]
+			wg.Done()
+		}(i)
+	}
+
+	done := make(chan struct{})
+	go func() {
+		wg.Wait()
+		close(done)
+	}()
+
+	tick := time.NewTicker(time.Second * 10)
+	select {
+	case <-done:
+	case <-tick.C:
+		for i, reactor := range reactors {
+			t.Log(cmn.Fmt("Consensus Reactor %v", i))
+			t.Log(cmn.Fmt("%v", reactor))
+		}
+		t.Fatalf("Timed out waiting for all validators to commit first block")
+	}
+}
+
+//-------------------------------
+// byzantine consensus functions
+
+func byzantineDecideProposalFunc(t *testing.T, height int64, round int, cs *ConsensusState, sw *p2p.Switch) {
+	// byzantine user should create two proposals and try to split the vote.
+	// Avoid sending on internalMsgQueue and running consensus state.
+
+	// Create a new proposal block from state/txs from the mempool.
+	block1, blockParts1 := cs.createProposalBlock()
+	polRound, polBlockID := cs.Votes.POLInfo()
+	proposal1 := types.NewProposal(height, round, blockParts1.Header(), polRound, polBlockID)
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal1); err != nil {
+		t.Error(err)
+	}
+
+	// Create a new proposal block from state/txs from the mempool.
+	block2, blockParts2 := cs.createProposalBlock()
+	polRound, polBlockID = cs.Votes.POLInfo()
+	proposal2 := types.NewProposal(height, round, blockParts2.Header(), polRound, polBlockID)
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal2); err != nil {
+		t.Error(err)
+	}
+
+	block1Hash := block1.Hash()
+	block2Hash := block2.Hash()
+
+	// broadcast conflicting proposals/block parts to peers
+	peers := sw.Peers().List()
+	t.Logf("Byzantine: broadcasting conflicting proposals to %d peers", len(peers))
+	for i, peer := range peers {
+		if i < len(peers)/2 {
+			go sendProposalAndParts(height, round, cs, peer, proposal1, block1Hash, blockParts1)
+		} else {
+			go sendProposalAndParts(height, round, cs, peer, proposal2, block2Hash, blockParts2)
+		}
+	}
+}
+
+func sendProposalAndParts(height int64, round int, cs *ConsensusState, peer p2p.Peer, proposal *types.Proposal, blockHash []byte, parts *types.PartSet) {
+	// proposal
+	msg := &ProposalMessage{Proposal: proposal}
+	peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+
+	// parts
+	for i := 0; i < parts.Total(); i++ {
+		part := parts.GetPart(i)
+		msg := &BlockPartMessage{
+			Height: height, // This tells peer that this part applies to us.
+			Round:  round,  // This tells peer that this part applies to us.
+			Part:   part,
+		}
+		peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+	}
+
+	// votes
+	cs.mtx.Lock()
+	prevote, _ := cs.signVote(types.VoteTypePrevote, blockHash, parts.Header())
+	precommit, _ := cs.signVote(types.VoteTypePrecommit, blockHash, parts.Header())
+	cs.mtx.Unlock()
+
+	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{prevote}})
+	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{precommit}})
+}
+
+//----------------------------------------
+// byzantine consensus reactor
+
+type ByzantineReactor struct {
+	cmn.Service
+	reactor *ConsensusReactor
+}
+
+func NewByzantineReactor(conR *ConsensusReactor) *ByzantineReactor {
+	return &ByzantineReactor{
+		Service: conR,
+		reactor: conR,
+	}
+}
+
+func (br *ByzantineReactor) SetSwitch(s *p2p.Switch)               { br.reactor.SetSwitch(s) }
+func (br *ByzantineReactor) GetChannels() []*p2p.ChannelDescriptor { return br.reactor.GetChannels() }
+func (br *ByzantineReactor) AddPeer(peer p2p.Peer) {
+	if !br.reactor.IsRunning() {
+		return
+	}
+
+	// Create peerState for peer
+	peerState := NewPeerState(peer).SetLogger(br.reactor.Logger)
+	peer.Set(types.PeerStateKey, peerState)
+
+	// Send our state to peer.
+	// If we're fast_syncing, broadcast a RoundStepMessage later upon SwitchToConsensus().
+	if !br.reactor.fastSync {
+		br.reactor.sendNewRoundStepMessages(peer)
+	}
+}
+func (br *ByzantineReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
+	br.reactor.RemovePeer(peer, reason)
+}
+func (br *ByzantineReactor) Receive(chID byte, peer p2p.Peer, msgBytes []byte) {
+	br.reactor.Receive(chID, peer, msgBytes)
+}
+
+//----------------------------------------
+// byzantine privValidator
+
+type ByzantinePrivValidator struct {
+	types.Signer
+
+	pv types.PrivValidator
+}
+
+// Return a priv validator that will sign anything
+func NewByzantinePrivValidator(pv types.PrivValidator) *ByzantinePrivValidator {
+	return &ByzantinePrivValidator{
+		Signer: pv.(*types.PrivValidatorFS).Signer,
+		pv:     pv,
+	}
+}
+
+func (privVal *ByzantinePrivValidator) GetAddress() data.Bytes {
+	return privVal.pv.GetAddress()
+}
+
+func (privVal *ByzantinePrivValidator) GetPubKey() crypto.PubKey {
+	return privVal.pv.GetPubKey()
+}
+
+func (privVal *ByzantinePrivValidator) SignVote(chainID string, vote *types.Vote) (err error) {
+	vote.Signature, err = privVal.Sign(types.SignBytes(chainID, vote))
+	return err
+}
+
+func (privVal *ByzantinePrivValidator) SignProposal(chainID string, proposal *types.Proposal) (err error) {
+	proposal.Signature, _ = privVal.Sign(types.SignBytes(chainID, proposal))
+	return nil
+}
+
+func (privVal *ByzantinePrivValidator) SignHeartbeat(chainID string, heartbeat *types.Heartbeat) (err error) {
+	heartbeat.Signature, _ = privVal.Sign(types.SignBytes(chainID, heartbeat))
+	return nil
+}
+
+func (privVal *ByzantinePrivValidator) String() string {
+	return cmn.Fmt("PrivValidator{%X}", privVal.GetAddress())
+}

consensus/common.go

@@ -1,15 +0,0 @@
-package consensus
-
-import (
-	"github.com/tendermint/go-events"
-)
-
-// NOTE: this is blocking
-func subscribeToEvent(evsw *events.EventSwitch, receiver, eventID string, chanCap int) chan interface{} {
-	// listen for new round
-	ch := make(chan interface{}, chanCap)
-	evsw.AddListenerForEvent(receiver, eventID, func(data events.EventData) {
-		ch <- data
-	})
-	return ch
-}

consensus/common_test.go

@@ -2,53 +2,87 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"fmt"
+	"io/ioutil"
+	"os"
+	"path"
 	"sort"
 	"sync"
 	"testing"
 	"time"
 
-	cfg "github.com/tendermint/go-config"
-	dbm "github.com/tendermint/go-db"
-	"github.com/tendermint/go-events"
+	abcicli "github.com/tendermint/abci/client"
+	abci "github.com/tendermint/abci/types"
 	bc "github.com/tendermint/tendermint/blockchain"
+	cfg "github.com/tendermint/tendermint/config"
+	cstypes "github.com/tendermint/tendermint/consensus/types"
 	mempl "github.com/tendermint/tendermint/mempool"
+	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
-	tmspcli "github.com/tendermint/tmsp/client"
-	tmsp "github.com/tendermint/tmsp/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
 
-	"github.com/tendermint/tmsp/example/counter"
+	"github.com/tendermint/abci/example/counter"
+	"github.com/tendermint/abci/example/dummy"
+
+	"github.com/go-kit/kit/log/term"
 )
 
-var config cfg.Config // NOTE: must be reset for each _test.go file
-var ensureTimeout = time.Duration(2)
+const (
+	testSubscriber = "test-client"
+)
 
-type validatorStub struct {
-	Height int
-	Round  int
-	*types.PrivValidator
+// genesis, chain_id, priv_val
+var config *cfg.Config // NOTE: must be reset for each _test.go file
+var ensureTimeout = time.Second * 2
+
+func ensureDir(dir string, mode os.FileMode) {
+	if err := cmn.EnsureDir(dir, mode); err != nil {
+		panic(err)
+	}
 }
 
-func NewValidatorStub(privValidator *types.PrivValidator) *validatorStub {
+func ResetConfig(name string) *cfg.Config {
+	return cfg.ResetTestRoot(name)
+}
+
+//-------------------------------------------------------------------------------
+// validator stub (a dummy consensus peer we control)
+
+type validatorStub struct {
+	Index  int // Validator index. NOTE: we don't assume validator set changes.
+	Height int64
+	Round  int
+	types.PrivValidator
+}
+
+var testMinPower int64 = 10
+
+func NewValidatorStub(privValidator types.PrivValidator, valIndex int) *validatorStub {
 	return &validatorStub{
+		Index:         valIndex,
 		PrivValidator: privValidator,
 	}
 }
 
 func (vs *validatorStub) signVote(voteType byte, hash []byte, header types.PartSetHeader) (*types.Vote, error) {
 	vote := &types.Vote{
+		ValidatorIndex:   vs.Index,
+		ValidatorAddress: vs.PrivValidator.GetAddress(),
 		Height:           vs.Height,
 		Round:            vs.Round,
+		Timestamp:        time.Now().UTC(),
 		Type:             voteType,
-		BlockHash:        hash,
-		BlockPartsHeader: header,
+		BlockID:          types.BlockID{hash, header},
 	}
-	err := vs.PrivValidator.SignVote(config.GetString("chain_id"), vote)
+	err := vs.PrivValidator.SignVote(config.ChainID, vote)
 	return vote, err
 }
 
-// convenienve function for testing
+// Sign vote for type/hash/header
 func signVote(vs *validatorStub, voteType byte, hash []byte, header types.PartSetHeader) *types.Vote {
 	v, err := vs.signVote(voteType, hash, header)
 	if err != nil {
@@ -57,102 +91,7 @@ func signVote(vs *validatorStub, voteType byte, hash []byte, header types.PartSe
 	return v
 }
 
-// create proposal block from cs1 but sign it with vs
-func decideProposal(cs1 *ConsensusState, cs2 *validatorStub, height, round int) (proposal *types.Proposal, block *types.Block) {
-	block, blockParts := cs1.createProposalBlock()
-	if block == nil { // on error
-		panic("error creating proposal block")
-	}
-
-	// Make proposal
-	proposal = types.NewProposal(height, round, blockParts.Header(), cs1.Votes.POLRound())
-	if err := cs2.SignProposal(config.GetString("chain_id"), proposal); err != nil {
-		panic(err)
-	}
-	return
-}
-
-//-------------------------------------------------------------------------------
-// utils
-
-/*
-func nilRound(t *testing.T, cs1 *ConsensusState, vss ...*validatorStub) {
-	cs1.mtx.Lock()
-	height, round := cs1.Height, cs1.Round
-	cs1.mtx.Unlock()
-
-	waitFor(t, cs1, height, round, RoundStepPrevote)
-
-	signAddVoteToFromMany(types.VoteTypePrevote, cs1, nil, cs1.ProposalBlockParts.Header(), vss...)
-
-	waitFor(t, cs1, height, round, RoundStepPrecommit)
-
-	signAddVoteToFromMany(types.VoteTypePrecommit, cs1, nil, cs1.ProposalBlockParts.Header(), vss...)
-
-	waitFor(t, cs1, height, round+1, RoundStepNewRound)
-}
-*/
-
-// NOTE: this switches the propser as far as `perspectiveOf` is concerned,
-// but for simplicity we return a block it generated.
-func changeProposer(t *testing.T, perspectiveOf *ConsensusState, newProposer *validatorStub) *types.Block {
-	_, v1 := perspectiveOf.Validators.GetByAddress(perspectiveOf.privValidator.Address)
-	v1.Accum, v1.VotingPower = 0, 0
-	if updated := perspectiveOf.Validators.Update(v1); !updated {
-		panic("failed to update validator")
-	}
-	_, v2 := perspectiveOf.Validators.GetByAddress(newProposer.Address)
-	v2.Accum, v2.VotingPower = 100, 100
-	if updated := perspectiveOf.Validators.Update(v2); !updated {
-		panic("failed to update validator")
-	}
-
-	// make the proposal
-	propBlock, _ := perspectiveOf.createProposalBlock()
-	if propBlock == nil {
-		panic("Failed to create proposal block with cs2")
-	}
-	return propBlock
-}
-
-func fixVotingPower(t *testing.T, cs1 *ConsensusState, addr2 []byte) {
-	_, v1 := cs1.Validators.GetByAddress(cs1.privValidator.Address)
-	_, v2 := cs1.Validators.GetByAddress(addr2)
-	v1.Accum, v1.VotingPower = v2.Accum, v2.VotingPower
-	if updated := cs1.Validators.Update(v1); !updated {
-		panic("failed to update validator")
-	}
-}
-
-func addVoteToFromMany(to *ConsensusState, votes []*types.Vote, froms ...*validatorStub) {
-	if len(votes) != len(froms) {
-		panic("len(votes) and len(froms) must match")
-	}
-
-	for i, from := range froms {
-		addVoteToFrom(to, from, votes[i])
-	}
-}
-
-func addVoteToFrom(to *ConsensusState, from *validatorStub, vote *types.Vote) {
-	to.mtx.Lock() // NOTE: wont need this when the vote comes with the index!
-	valIndex, _ := to.Validators.GetByAddress(from.PrivValidator.Address)
-	to.mtx.Unlock()
-
-	to.peerMsgQueue <- msgInfo{Msg: &VoteMessage{valIndex, vote}}
-	// added, err := to.TryAddVote(valIndex, vote, "")
-	/*
-		if _, ok := err.(*types.ErrVoteConflictingSignature); ok {
-			// let it fly
-		} else if !added {
-			fmt.Println("to, from, vote:", to.Height, from.Height, vote.Height)
-			panic(fmt.Sprintln("Failed to add vote. Err:", err))
-		} else if err != nil {
-			panic(fmt.Sprintln("Failed to add vote:", err))
-		}*/
-}
-
-func signVoteMany(voteType byte, hash []byte, header types.PartSetHeader, vss ...*validatorStub) []*types.Vote {
+func signVotes(voteType byte, hash []byte, header types.PartSetHeader, vss ...*validatorStub) []*types.Vote {
 	votes := make([]*types.Vote, len(vss))
 	for i, vs := range vss {
 		votes[i] = signVote(vs, voteType, hash, header)
@@ -160,79 +99,6 @@ func signVoteMany(voteType byte, hash []byte, header types.PartSetHeader, vss ..
 	return votes
 }
 
-// add vote to one cs from another
-// if voteCh is not nil, read all votes
-func signAddVoteToFromMany(voteType byte, to *ConsensusState, hash []byte, header types.PartSetHeader, voteCh chan interface{}, froms ...*validatorStub) {
-	var wg chan struct{} // when done reading all votes
-	if voteCh != nil {
-		wg = readVotes(voteCh, len(froms))
-	}
-	for _, from := range froms {
-		vote := signVote(from, voteType, hash, header)
-		addVoteToFrom(to, from, vote)
-	}
-
-	if voteCh != nil {
-		<-wg
-	}
-}
-
-func signAddVoteToFrom(voteType byte, to *ConsensusState, from *validatorStub, hash []byte, header types.PartSetHeader, voteCh chan interface{}) *types.Vote {
-	var wg chan struct{} // when done reading all votes
-	if voteCh != nil {
-		wg = readVotes(voteCh, 1)
-	}
-	vote := signVote(from, voteType, hash, header)
-	addVoteToFrom(to, from, vote)
-	if voteCh != nil {
-		<-wg
-	}
-	return vote
-}
-
-func ensureNoNewStep(stepCh chan interface{}) {
-	timeout := time.NewTicker(ensureTimeout * time.Second)
-	select {
-	case <-timeout.C:
-		break
-	case <-stepCh:
-		panic("We should be stuck waiting for more votes, not moving to the next step")
-	}
-}
-
-/*
-func ensureNoNewStep(t *testing.T, cs *ConsensusState) {
-	timeout := time.NewTicker(ensureTimeout * time.Second)
-	select {
-	case <-timeout.C:
-		break
-	case <-cs.NewStepCh():
-		panic("We should be stuck waiting for more votes, not moving to the next step")
-	}
-}
-
-func ensureNewStep(t *testing.T, cs *ConsensusState) *RoundState {
-	timeout := time.NewTicker(ensureTimeout * time.Second)
-	select {
-	case <-timeout.C:
-		panic("We should have gone to the next step, not be stuck waiting")
-	case rs := <-cs.NewStepCh():
-		return rs
-	}
-}
-
-func waitFor(t *testing.T, cs *ConsensusState, height int, round int, step RoundStepType) {
-	for {
-		rs := ensureNewStep(t, cs)
-		if CompareHRS(rs.Height, rs.Round, rs.Step, height, round, step) < 0 {
-			continue
-		} else {
-			break
-		}
-	}
-}
-*/
-
 func incrementHeight(vss ...*validatorStub) {
 	for _, vs := range vss {
 		vs.Height += 1
@@ -245,19 +111,54 @@ func incrementRound(vss ...*validatorStub) {
 	}
 }
 
+//-------------------------------------------------------------------------------
+// Functions for transitioning the consensus state
+
+func startTestRound(cs *ConsensusState, height int64, round int) {
+	cs.enterNewRound(height, round)
+	cs.startRoutines(0)
+}
+
+// Create proposal block from cs1 but sign it with vs
+func decideProposal(cs1 *ConsensusState, vs *validatorStub, height int64, round int) (proposal *types.Proposal, block *types.Block) {
+	block, blockParts := cs1.createProposalBlock()
+	if block == nil { // on error
+		panic("error creating proposal block")
+	}
+
+	// Make proposal
+	polRound, polBlockID := cs1.Votes.POLInfo()
+	proposal = types.NewProposal(height, round, blockParts.Header(), polRound, polBlockID)
+	if err := vs.SignProposal(config.ChainID, proposal); err != nil {
+		panic(err)
+	}
+	return
+}
+
+func addVotes(to *ConsensusState, votes ...*types.Vote) {
+	for _, vote := range votes {
+		to.peerMsgQueue <- msgInfo{Msg: &VoteMessage{vote}}
+	}
+}
+
+func signAddVotes(to *ConsensusState, voteType byte, hash []byte, header types.PartSetHeader, vss ...*validatorStub) {
+	votes := signVotes(voteType, hash, header, vss...)
+	addVotes(to, votes...)
+}
+
 func validatePrevote(t *testing.T, cs *ConsensusState, round int, privVal *validatorStub, blockHash []byte) {
 	prevotes := cs.Votes.Prevotes(round)
 	var vote *types.Vote
-	if vote = prevotes.GetByAddress(privVal.Address); vote == nil {
+	if vote = prevotes.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find prevote from validator")
 	}
 	if blockHash == nil {
-		if vote.BlockHash != nil {
-			panic(fmt.Sprintf("Expected prevote to be for nil, got %X", vote.BlockHash))
+		if vote.BlockID.Hash != nil {
+			panic(fmt.Sprintf("Expected prevote to be for nil, got %X", vote.BlockID.Hash))
 		}
 	} else {
-		if !bytes.Equal(vote.BlockHash, blockHash) {
-			panic(fmt.Sprintf("Expected prevote to be for %X, got %X", blockHash, vote.BlockHash))
+		if !bytes.Equal(vote.BlockID.Hash, blockHash) {
+			panic(fmt.Sprintf("Expected prevote to be for %X, got %X", blockHash, vote.BlockID.Hash))
 		}
 	}
 }
@@ -265,27 +166,27 @@ func validatePrevote(t *testing.T, cs *ConsensusState, round int, privVal *valid
 func validateLastPrecommit(t *testing.T, cs *ConsensusState, privVal *validatorStub, blockHash []byte) {
 	votes := cs.LastCommit
 	var vote *types.Vote
-	if vote = votes.GetByAddress(privVal.Address); vote == nil {
+	if vote = votes.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find precommit from validator")
 	}
-	if !bytes.Equal(vote.BlockHash, blockHash) {
-		panic(fmt.Sprintf("Expected precommit to be for %X, got %X", blockHash, vote.BlockHash))
+	if !bytes.Equal(vote.BlockID.Hash, blockHash) {
+		panic(fmt.Sprintf("Expected precommit to be for %X, got %X", blockHash, vote.BlockID.Hash))
 	}
 }
 
 func validatePrecommit(t *testing.T, cs *ConsensusState, thisRound, lockRound int, privVal *validatorStub, votedBlockHash, lockedBlockHash []byte) {
 	precommits := cs.Votes.Precommits(thisRound)
 	var vote *types.Vote
-	if vote = precommits.GetByAddress(privVal.Address); vote == nil {
+	if vote = precommits.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find precommit from validator")
 	}
 
 	if votedBlockHash == nil {
-		if vote.BlockHash != nil {
+		if vote.BlockID.Hash != nil {
 			panic("Expected precommit to be for nil")
 		}
 	} else {
-		if !bytes.Equal(vote.BlockHash, votedBlockHash) {
+		if !bytes.Equal(vote.BlockID.Hash, votedBlockHash) {
 			panic("Expected precommit to be for proposal block")
 		}
 	}
@@ -311,36 +212,84 @@ func validatePrevoteAndPrecommit(t *testing.T, cs *ConsensusState, thisRound, lo
 	cs.mtx.Unlock()
 }
 
-func fixedConsensusState() *ConsensusState {
-	stateDB := dbm.NewMemDB()
-	state := sm.MakeGenesisStateFromFile(stateDB, config.GetString("genesis_file"))
-	privValidatorFile := config.GetString("priv_validator_file")
-	privValidator := types.LoadOrGenPrivValidator(privValidatorFile)
-	privValidator.Reset()
-	cs := newConsensusState(state, privValidator, counter.NewCounterApplication(true))
-	return cs
+// genesis
+func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
+	voteCh0 := make(chan interface{})
+	err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryVote, voteCh0)
+	if err != nil {
+		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, types.EventQueryVote))
+	}
+	voteCh := make(chan interface{})
+	go func() {
+		for v := range voteCh0 {
+			vote := v.(types.TMEventData).Unwrap().(types.EventDataVote)
+			// we only fire for our own votes
+			if bytes.Equal(addr, vote.Vote.ValidatorAddress) {
+				voteCh <- v
+			}
+		}
+	}()
+	return voteCh
 }
 
-func newConsensusState(state *sm.State, pv *types.PrivValidator, app tmsp.Application) *ConsensusState {
-	// Get BlockStore
+//-------------------------------------------------------------------------------
+// consensus states
+
+func newConsensusState(state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
+	return newConsensusStateWithConfig(config, state, pv, app)
+}
+
+func newConsensusStateWithConfig(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
 	blockDB := dbm.NewMemDB()
+	return newConsensusStateWithConfigAndBlockStore(thisConfig, state, pv, app, blockDB)
+}
+
+func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application, blockDB dbm.DB) *ConsensusState {
+	// Get BlockStore
 	blockStore := bc.NewBlockStore(blockDB)
 
 	// one for mempool, one for consensus
 	mtx := new(sync.Mutex)
-	proxyAppConnMem := tmspcli.NewLocalClient(mtx, app)
-	proxyAppConnCon := tmspcli.NewLocalClient(mtx, app)
+	proxyAppConnMem := abcicli.NewLocalClient(mtx, app)
+	proxyAppConnCon := abcicli.NewLocalClient(mtx, app)
 
 	// Make Mempool
-	mempool := mempl.NewMempool(config, proxyAppConnMem)
+	mempool := mempl.NewMempool(thisConfig.Mempool, proxyAppConnMem, 0)
+	mempool.SetLogger(log.TestingLogger().With("module", "mempool"))
+	if thisConfig.Consensus.WaitForTxs() {
+		mempool.EnableTxsAvailable()
+	}
+
+	// mock the evidence pool
+	evpool := types.MockEvidencePool{}
 
 	// Make ConsensusReactor
-	cs := NewConsensusState(config, state, proxyAppConnCon, blockStore, mempool)
+	stateDB := dbm.NewMemDB()
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyAppConnCon, mempool, evpool)
+	cs := NewConsensusState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool)
+	cs.SetLogger(log.TestingLogger())
 	cs.SetPrivValidator(pv)
 
-	evsw := events.NewEventSwitch()
-	cs.SetEventSwitch(evsw)
-	evsw.Start()
+	eventBus := types.NewEventBus()
+	eventBus.SetLogger(log.TestingLogger().With("module", "events"))
+	eventBus.Start()
+	cs.SetEventBus(eventBus)
+	return cs
+}
+
+func loadPrivValidator(config *cfg.Config) *types.PrivValidatorFS {
+	privValidatorFile := config.PrivValidatorFile()
+	ensureDir(path.Dir(privValidatorFile), 0700)
+	privValidator := types.LoadOrGenPrivValidatorFS(privValidatorFile)
+	privValidator.Reset()
+	return privValidator
+}
+
+func fixedConsensusStateDummy(config *cfg.Config, logger log.Logger) *ConsensusState {
+	state, _ := sm.MakeGenesisStateFromFile(config.GenesisFile())
+	privValidator := loadPrivValidator(config)
+	cs := newConsensusState(state, privValidator, dummy.NewDummyApplication())
+	cs.SetLogger(logger)
 	return cs
 }
 
@@ -351,9 +300,10 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	vss := make([]*validatorStub, nValidators)
 
 	cs := newConsensusState(state, privVals[0], counter.NewCounterApplication(true))
+	cs.SetLogger(log.TestingLogger())
 
 	for i := 0; i < nValidators; i++ {
-		vss[i] = NewValidatorStub(privVals[i])
+		vss[i] = NewValidatorStub(privVals[i], i)
 	}
 	// since cs1 starts at 1
 	incrementHeight(vss[1:]...)
@@ -361,62 +311,192 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	return cs, vss
 }
 
-func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
-	voteCh0 := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 1)
-	voteCh := make(chan interface{})
-	go func() {
-		for {
-			v := <-voteCh0
-			vote := v.(types.EventDataVote)
-			// we only fire for our own votes
-			if bytes.Equal(addr, vote.Address) {
-				voteCh <- v
+//-------------------------------------------------------------------------------
+
+func ensureNoNewStep(stepCh <-chan interface{}) {
+	timer := time.NewTimer(ensureTimeout)
+	select {
+	case <-timer.C:
+		break
+	case <-stepCh:
+		panic("We should be stuck waiting, not moving to the next step")
+	}
+}
+
+func ensureNewStep(stepCh <-chan interface{}) {
+	timer := time.NewTimer(ensureTimeout)
+	select {
+	case <-timer.C:
+		panic("We shouldnt be stuck waiting")
+	case <-stepCh:
+		break
+	}
+}
+
+//-------------------------------------------------------------------------------
+// consensus nets
+
+// consensusLogger is a TestingLogger which uses a different
+// color for each validator ("validator" key must exist).
+func consensusLogger() log.Logger {
+	return log.TestingLoggerWithColorFn(func(keyvals ...interface{}) term.FgBgColor {
+		for i := 0; i < len(keyvals)-1; i += 2 {
+			if keyvals[i] == "validator" {
+				return term.FgBgColor{Fg: term.Color(uint8(keyvals[i+1].(int) + 1))}
 			}
 		}
-	}()
-	return voteCh
+		return term.FgBgColor{}
+	})
 }
 
-func readVotes(ch chan interface{}, reads int) chan struct{} {
-	wg := make(chan struct{})
-	go func() {
-		for i := 0; i < reads; i++ {
-			<-ch // read the precommit event
+func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application, configOpts ...func(*cfg.Config)) []*ConsensusState {
+	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
+	css := make([]*ConsensusState, nValidators)
+	logger := consensusLogger()
+	for i := 0; i < nValidators; i++ {
+		stateDB := dbm.NewMemDB() // each state needs its own db
+		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
+		thisConfig := ResetConfig(cmn.Fmt("%s_%d", testName, i))
+		for _, opt := range configOpts {
+			opt(thisConfig)
 		}
-		close(wg)
-	}()
-	return wg
+		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
+		app := appFunc()
+		vals := types.TM2PB.Validators(state.Validators)
+		app.InitChain(abci.RequestInitChain{Validators: vals})
+
+		css[i] = newConsensusStateWithConfig(thisConfig, state, privVals[i], app)
+		css[i].SetLogger(logger.With("validator", i))
+		css[i].SetTimeoutTicker(tickerFunc())
+	}
+	return css
 }
 
-func randGenesisState(numValidators int, randPower bool, minPower int64) (*sm.State, []*types.PrivValidator) {
-	db := dbm.NewMemDB()
-	genDoc, privValidators := randGenesisDoc(numValidators, randPower, minPower)
-	s0 := sm.MakeGenesisState(db, genDoc)
-	s0.Save()
-	return s0, privValidators
+// nPeers = nValidators + nNotValidator
+func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application) []*ConsensusState {
+	genDoc, privVals := randGenesisDoc(nValidators, false, testMinPower)
+	css := make([]*ConsensusState, nPeers)
+	logger := consensusLogger()
+	for i := 0; i < nPeers; i++ {
+		stateDB := dbm.NewMemDB() // each state needs its own db
+		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
+		thisConfig := ResetConfig(cmn.Fmt("%s_%d", testName, i))
+		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
+		var privVal types.PrivValidator
+		if i < nValidators {
+			privVal = privVals[i]
+		} else {
+			_, tempFilePath := cmn.Tempfile("priv_validator_")
+			privVal = types.GenPrivValidatorFS(tempFilePath)
+		}
+
+		app := appFunc()
+		vals := types.TM2PB.Validators(state.Validators)
+		app.InitChain(abci.RequestInitChain{Validators: vals})
+
+		css[i] = newConsensusStateWithConfig(thisConfig, state, privVal, app)
+		css[i].SetLogger(logger.With("validator", i))
+		css[i].SetTimeoutTicker(tickerFunc())
+	}
+	return css
 }
 
-func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []*types.PrivValidator) {
+func getSwitchIndex(switches []*p2p.Switch, peer p2p.Peer) int {
+	for i, s := range switches {
+		if bytes.Equal(peer.NodeInfo().PubKey.Address(), s.NodeInfo().PubKey.Address()) {
+			return i
+		}
+	}
+	panic("didnt find peer in switches")
+	return -1
+}
+
+//-------------------------------------------------------------------------------
+// genesis
+
+func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []*types.PrivValidatorFS) {
 	validators := make([]types.GenesisValidator, numValidators)
-	privValidators := make([]*types.PrivValidator, numValidators)
+	privValidators := make([]*types.PrivValidatorFS, numValidators)
 	for i := 0; i < numValidators; i++ {
 		val, privVal := types.RandValidator(randPower, minPower)
 		validators[i] = types.GenesisValidator{
 			PubKey: val.PubKey,
-			Amount: val.VotingPower,
+			Power:  val.VotingPower,
 		}
 		privValidators[i] = privVal
 	}
 	sort.Sort(types.PrivValidatorsByAddress(privValidators))
 	return &types.GenesisDoc{
 		GenesisTime: time.Now(),
-		ChainID:     config.GetString("chain_id"),
+		ChainID:     config.ChainID,
 		Validators:  validators,
 	}, privValidators
-
 }
 
-func startTestRound(cs *ConsensusState, height, round int) {
-	cs.enterNewRound(height, round)
-	cs.startRoutines(0)
+func randGenesisState(numValidators int, randPower bool, minPower int64) (sm.State, []*types.PrivValidatorFS) {
+	genDoc, privValidators := randGenesisDoc(numValidators, randPower, minPower)
+	s0, _ := sm.MakeGenesisState(genDoc)
+	db := dbm.NewMemDB()
+	sm.SaveState(db, s0)
+	return s0, privValidators
+}
+
+//------------------------------------
+// mock ticker
+
+func newMockTickerFunc(onlyOnce bool) func() TimeoutTicker {
+	return func() TimeoutTicker {
+		return &mockTicker{
+			c:        make(chan timeoutInfo, 10),
+			onlyOnce: onlyOnce,
+		}
+	}
+}
+
+// mock ticker only fires on RoundStepNewHeight
+// and only once if onlyOnce=true
+type mockTicker struct {
+	c chan timeoutInfo
+
+	mtx      sync.Mutex
+	onlyOnce bool
+	fired    bool
+}
+
+func (m *mockTicker) Start() error {
+	return nil
+}
+
+func (m *mockTicker) Stop() error {
+	return nil
+}
+
+func (m *mockTicker) ScheduleTimeout(ti timeoutInfo) {
+	m.mtx.Lock()
+	defer m.mtx.Unlock()
+	if m.onlyOnce && m.fired {
+		return
+	}
+	if ti.Step == cstypes.RoundStepNewHeight {
+		m.c <- ti
+		m.fired = true
+	}
+}
+
+func (m *mockTicker) Chan() <-chan timeoutInfo {
+	return m.c
+}
+
+func (mockTicker) SetLogger(log.Logger) {
+}
+
+//------------------------------------
+
+func newCounter() abci.Application {
+	return counter.NewCounterApplication(true)
+}
+
+func newPersistentDummy() abci.Application {
+	dir, _ := ioutil.TempDir("/tmp", "persistent-dummy")
+	return dummy.NewPersistentDummyApplication(dir)
 }

consensus/height_vote_set_test.go

@@ -1,53 +0,0 @@
-package consensus
-
-import (
-	"testing"
-
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/tendermint/config/tendermint_test"
-	"github.com/tendermint/tendermint/types"
-)
-
-func init() {
-	config = tendermint_test.ResetConfig("consensus_height_vote_set_test")
-}
-
-func TestPeerCatchupRounds(t *testing.T) {
-	valSet, privVals := types.RandValidatorSet(10, 1)
-
-	hvs := NewHeightVoteSet(config.GetString("chain_id"), 1, valSet)
-
-	vote999_0 := makeVoteHR(t, 1, 999, privVals[0])
-	added, _, err := hvs.AddByIndex(0, vote999_0, "peer1")
-	if !added || err != nil {
-		t.Error("Expected to successfully add vote from peer", added, err)
-	}
-
-	vote1000_0 := makeVoteHR(t, 1, 1000, privVals[0])
-	added, _, err = hvs.AddByIndex(0, vote1000_0, "peer1")
-	if added {
-		t.Error("Expected to *not* add vote from peer, too many catchup rounds.")
-	}
-
-	added, _, err = hvs.AddByIndex(0, vote1000_0, "peer2")
-	if !added || err != nil {
-		t.Error("Expected to successfully add vote from another peer")
-	}
-
-}
-
-func makeVoteHR(t *testing.T, height, round int, privVal *types.PrivValidator) *types.Vote {
-	vote := &types.Vote{
-		Height:    height,
-		Round:     round,
-		Type:      types.VoteTypePrecommit,
-		BlockHash: []byte("fakehash"),
-	}
-	chainID := config.GetString("chain_id")
-	err := privVal.SignVote(chainID, vote)
-	if err != nil {
-		panic(Fmt("Error signing vote: %v", err))
-		return nil
-	}
-	return vote
-}

consensus/log.go

@@ -1,18 +0,0 @@
-package consensus
-
-import (
-	"github.com/tendermint/go-logger"
-)
-
-var log = logger.New("module", "consensus")
-
-/*
-func init() {
-	log.SetHandler(
-		logger.LvlFilterHandler(
-			logger.LvlDebug,
-			logger.BypassHandler(),
-		),
-	)
-}
-*/

consensus/mempool_test.go

@@ -2,58 +2,184 @@ package consensus
 
 import (
 	"encoding/binary"
-	//	"math/rand"
+	"fmt"
 	"testing"
 	"time"
 
-	"github.com/tendermint/tendermint/config/tendermint_test"
-	"github.com/tendermint/tendermint/types"
-	tmsp "github.com/tendermint/tmsp/types"
+	"github.com/stretchr/testify/assert"
 
-	. "github.com/tendermint/go-common"
+	"github.com/tendermint/abci/example/code"
+	abci "github.com/tendermint/abci/types"
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/tendermint/tendermint/types"
 )
 
 func init() {
-	config = tendermint_test.ResetConfig("consensus_mempool_test")
+	config = ResetConfig("consensus_mempool_test")
+}
+
+func TestNoProgressUntilTxsAvailable(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocks = false
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	startTestRound(cs, height, round)
+
+	ensureNewStep(newBlockCh) // first block gets committed
+	ensureNoNewStep(newBlockCh)
+	deliverTxsRange(cs, 0, 1)
+	ensureNewStep(newBlockCh) // commit txs
+	ensureNewStep(newBlockCh) // commit updated app hash
+	ensureNoNewStep(newBlockCh)
+}
+
+func TestProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocksInterval = int(ensureTimeout.Seconds())
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	startTestRound(cs, height, round)
+
+	ensureNewStep(newBlockCh)   // first block gets committed
+	ensureNoNewStep(newBlockCh) // then we dont make a block ...
+	ensureNewStep(newBlockCh)   // until the CreateEmptyBlocksInterval has passed
+}
+
+func TestProgressInHigherRound(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocks = false
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	newRoundCh := subscribe(cs.eventBus, types.EventQueryNewRound)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
+	cs.setProposal = func(proposal *types.Proposal) error {
+		if cs.Height == 2 && cs.Round == 0 {
+			// dont set the proposal in round 0 so we timeout and
+			// go to next round
+			cs.Logger.Info("Ignoring set proposal at height 2, round 0")
+			return nil
+		}
+		return cs.defaultSetProposal(proposal)
+	}
+	startTestRound(cs, height, round)
+
+	ensureNewStep(newRoundCh) // first round at first height
+	ensureNewStep(newBlockCh) // first block gets committed
+	ensureNewStep(newRoundCh) // first round at next height
+	deliverTxsRange(cs, 0, 1) // we deliver txs, but dont set a proposal so we get the next round
+	<-timeoutCh
+	ensureNewStep(newRoundCh) // wait for the next round
+	ensureNewStep(newBlockCh) // now we can commit the block
+}
+
+func deliverTxsRange(cs *ConsensusState, start, end int) {
+	// Deliver some txs.
+	for i := start; i < end; i++ {
+		txBytes := make([]byte, 8)
+		binary.BigEndian.PutUint64(txBytes, uint64(i))
+		err := cs.mempool.CheckTx(txBytes, nil)
+		if err != nil {
+			panic(cmn.Fmt("Error after CheckTx: %v", err))
+		}
+	}
 }
 
 func TestTxConcurrentWithCommit(t *testing.T) {
-
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusState(state, privVals[0], NewCounterApplication())
 	height, round := cs.Height, cs.Round
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-
-	appendTxsRange := func(start, end int) {
-		// Append some txs.
-		for i := start; i < end; i++ {
-			txBytes := make([]byte, 8)
-			binary.BigEndian.PutUint64(txBytes, uint64(i))
-			err := cs.mempool.CheckTx(txBytes, nil)
-			if err != nil {
-				panic(Fmt("Error after CheckTx: %v", err))
-			}
-			//	time.Sleep(time.Microsecond * time.Duration(rand.Int63n(3000)))
-		}
-	}
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
 
 	NTxs := 10000
-	go appendTxsRange(0, NTxs)
+	go deliverTxsRange(cs, 0, NTxs)
 
 	startTestRound(cs, height, round)
-	ticker := time.NewTicker(time.Second * 20)
 	for nTxs := 0; nTxs < NTxs; {
+		ticker := time.NewTicker(time.Second * 30)
 		select {
 		case b := <-newBlockCh:
-			nTxs += b.(types.EventDataNewBlock).Block.Header.NumTxs
+			evt := b.(types.TMEventData).Unwrap().(types.EventDataNewBlock)
+			nTxs += int(evt.Block.Header.NumTxs)
 		case <-ticker.C:
 			panic("Timed out waiting to commit blocks with transactions")
 		}
 	}
 }
 
+func TestRmBadTx(t *testing.T) {
+	state, privVals := randGenesisState(1, false, 10)
+	app := NewCounterApplication()
+	cs := newConsensusState(state, privVals[0], app)
+
+	// increment the counter by 1
+	txBytes := make([]byte, 8)
+	binary.BigEndian.PutUint64(txBytes, uint64(0))
+
+	resDeliver := app.DeliverTx(txBytes)
+	assert.False(t, resDeliver.IsErr(), cmn.Fmt("expected no error. got %v", resDeliver))
+
+	resCommit := app.Commit()
+	assert.False(t, resCommit.IsErr(), cmn.Fmt("expected no error. got %v", resCommit))
+
+	emptyMempoolCh := make(chan struct{})
+	checkTxRespCh := make(chan struct{})
+	go func() {
+		// Try to send the tx through the mempool.
+		// CheckTx should not err, but the app should return a bad abci code
+		// and the tx should get removed from the pool
+		err := cs.mempool.CheckTx(txBytes, func(r *abci.Response) {
+			if r.GetCheckTx().Code != code.CodeTypeBadNonce {
+				t.Fatalf("expected checktx to return bad nonce, got %v", r)
+			}
+			checkTxRespCh <- struct{}{}
+		})
+		if err != nil {
+			t.Fatalf("Error after CheckTx: %v", err)
+		}
+
+		// check for the tx
+		for {
+			txs := cs.mempool.Reap(1)
+			if len(txs) == 0 {
+				emptyMempoolCh <- struct{}{}
+			}
+			time.Sleep(10 * time.Millisecond)
+		}
+	}()
+
+	// Wait until the tx returns
+	ticker := time.After(time.Second * 5)
+	select {
+	case <-checkTxRespCh:
+		// success
+	case <-ticker:
+		t.Fatalf("Timed out waiting for tx to return")
+	}
+
+	// Wait until the tx is removed
+	ticker = time.After(time.Second * 5)
+	select {
+	case <-emptyMempoolCh:
+		// success
+	case <-ticker:
+		t.Fatalf("Timed out waiting for tx to be removed")
+	}
+}
+
 // CounterApplication that maintains a mempool state and resets it upon commit
 type CounterApplication struct {
+	abci.BaseApplication
+
 	txCount        int
 	mempoolTxCount int
 }
@@ -62,49 +188,45 @@ func NewCounterApplication() *CounterApplication {
 	return &CounterApplication{}
 }
 
-func (app *CounterApplication) Info() string {
-	return Fmt("txs:%v", app.txCount)
+func (app *CounterApplication) Info(req abci.RequestInfo) abci.ResponseInfo {
+	return abci.ResponseInfo{Data: cmn.Fmt("txs:%v", app.txCount)}
 }
 
-func (app *CounterApplication) SetOption(key string, value string) (log string) {
-	return ""
+func (app *CounterApplication) DeliverTx(tx []byte) abci.ResponseDeliverTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.txCount) {
+		return abci.ResponseDeliverTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.txCount, txValue)}
+	}
+	app.txCount += 1
+	return abci.ResponseDeliverTx{Code: code.CodeTypeOK}
 }
 
-func (app *CounterApplication) AppendTx(tx []byte) tmsp.Result {
-	return runTx(tx, &app.txCount)
+func (app *CounterApplication) CheckTx(tx []byte) abci.ResponseCheckTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.mempoolTxCount) {
+		return abci.ResponseCheckTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.mempoolTxCount, txValue)}
+	}
+	app.mempoolTxCount += 1
+	return abci.ResponseCheckTx{Code: code.CodeTypeOK}
 }
 
-func (app *CounterApplication) CheckTx(tx []byte) tmsp.Result {
-	return runTx(tx, &app.mempoolTxCount)
-}
-
-func runTx(tx []byte, countPtr *int) tmsp.Result {
-	count := *countPtr
+func txAsUint64(tx []byte) uint64 {
 	tx8 := make([]byte, 8)
 	copy(tx8[len(tx8)-len(tx):], tx)
-	txValue := binary.BigEndian.Uint64(tx8)
-	if txValue != uint64(count) {
-		return tmsp.Result{
-			Code: tmsp.CodeType_BadNonce,
-			Data: nil,
-			Log:  Fmt("Invalid nonce. Expected %v, got %v", count, txValue),
-		}
-	}
-	*countPtr += 1
-	return tmsp.OK
+	return binary.BigEndian.Uint64(tx8)
 }
 
-func (app *CounterApplication) Commit() tmsp.Result {
+func (app *CounterApplication) Commit() abci.ResponseCommit {
 	app.mempoolTxCount = app.txCount
 	if app.txCount == 0 {
-		return tmsp.OK
+		return abci.ResponseCommit{Code: code.CodeTypeOK}
 	} else {
 		hash := make([]byte, 8)
 		binary.BigEndian.PutUint64(hash, uint64(app.txCount))
-		return tmsp.NewResultOK(hash, "")
+		return abci.ResponseCommit{Code: code.CodeTypeOK, Data: hash}
 	}
 }
-
-func (app *CounterApplication) Query(query []byte) tmsp.Result {
-	return tmsp.NewResultOK(nil, Fmt("Query is not supported"))
-}

consensus/reactor_test.go

@@ -0,0 +1,430 @@
+package consensus
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"runtime/pprof"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/tendermint/abci/example/dummy"
+	"github.com/tendermint/tmlibs/log"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/types"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func init() {
+	config = ResetConfig("consensus_reactor_test")
+}
+
+//----------------------------------------------
+// in-process testnets
+
+func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*ConsensusReactor, []chan interface{}, []*types.EventBus) {
+	reactors := make([]*ConsensusReactor, N)
+	eventChans := make([]chan interface{}, N)
+	eventBuses := make([]*types.EventBus, N)
+	logger := consensusLogger()
+	for i := 0; i < N; i++ {
+		/*thisLogger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
+		if err != nil {	t.Fatal(err)}*/
+		thisLogger := logger
+
+		reactors[i] = NewConsensusReactor(css[i], true) // so we dont start the consensus states
+		reactors[i].conS.SetLogger(thisLogger.With("validator", i))
+		reactors[i].SetLogger(thisLogger.With("validator", i))
+
+		eventBuses[i] = types.NewEventBus()
+		eventBuses[i].SetLogger(thisLogger.With("module", "events", "validator", i))
+		err := eventBuses[i].Start()
+		require.NoError(t, err)
+
+		reactors[i].SetEventBus(eventBuses[i])
+
+		eventChans[i] = make(chan interface{}, 1)
+		err = eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
+	}
+	// make connected switches and start all reactors
+	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
+		s.AddReactor("CONSENSUS", reactors[i])
+		s.SetLogger(reactors[i].Logger.With("module", "p2p", "validator", i))
+		return s
+	}, p2p.Connect2Switches)
+
+	// now that everyone is connected,  start the state machines
+	// If we started the state machines before everyone was connected,
+	// we'd block when the cs fires NewBlockEvent and the peers are trying to start their reactors
+	// TODO: is this still true with new pubsub?
+	for i := 0; i < N; i++ {
+		s := reactors[i].conS.GetState()
+		reactors[i].SwitchToConsensus(s, 0)
+	}
+	return reactors, eventChans, eventBuses
+}
+
+func stopConsensusNet(logger log.Logger, reactors []*ConsensusReactor, eventBuses []*types.EventBus) {
+	logger.Info("stopConsensusNet", "n", len(reactors))
+	for i, r := range reactors {
+		logger.Info("stopConsensusNet: Stopping ConsensusReactor", "i", i)
+		r.Switch.Stop()
+	}
+	for i, b := range eventBuses {
+		logger.Info("stopConsensusNet: Stopping eventBus", "i", i)
+		b.Stop()
+	}
+	logger.Info("stopConsensusNet: DONE", "n", len(reactors))
+}
+
+// Ensure a testnet makes blocks
+func TestReactor(t *testing.T) {
+	N := 4
+	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
+	// wait till everyone makes the first new block
+	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+		<-eventChans[j]
+		wg.Done()
+	}, css)
+}
+
+// Ensure a testnet sends proposal heartbeats and makes blocks when there are txs
+func TestReactorProposalHeartbeats(t *testing.T) {
+	N := 4
+	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter,
+		func(c *cfg.Config) {
+			c.Consensus.CreateEmptyBlocks = false
+		})
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
+	heartbeatChans := make([]chan interface{}, N)
+	var err error
+	for i := 0; i < N; i++ {
+		heartbeatChans[i] = make(chan interface{}, 1)
+		err = eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryProposalHeartbeat, heartbeatChans[i])
+		require.NoError(t, err)
+	}
+	// wait till everyone sends a proposal heartbeat
+	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+		<-heartbeatChans[j]
+		wg.Done()
+	}, css)
+
+	// send a tx
+	if err := css[3].mempool.CheckTx([]byte{1, 2, 3}, nil); err != nil {
+		//t.Fatal(err)
+	}
+
+	// wait till everyone makes the first new block
+	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+		<-eventChans[j]
+		wg.Done()
+	}, css)
+}
+
+//-------------------------------------------------------------
+// ensure we can make blocks despite cycling a validator set
+
+func TestReactorVotingPowerChange(t *testing.T) {
+	nVals := 4
+	logger := log.TestingLogger()
+	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentDummy)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nVals)
+	defer stopConsensusNet(logger, reactors, eventBuses)
+
+	// map of active validators
+	activeVals := make(map[string]struct{})
+	for i := 0; i < nVals; i++ {
+		activeVals[string(css[i].privValidator.GetAddress())] = struct{}{}
+	}
+
+	// wait till everyone makes block 1
+	timeoutWaitGroup(t, nVals, func(wg *sync.WaitGroup, j int) {
+		<-eventChans[j]
+		wg.Done()
+	}, css)
+
+	//---------------------------------------------------------------------------
+	logger.Debug("---------------------------- Testing changing the voting power of one validator a few times")
+
+	val1PubKey := css[0].privValidator.GetPubKey()
+	updateValidatorTx := dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 25)
+	previousTotalVotingPower := css[0].GetRoundState().LastValidators.TotalVotingPower()
+
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+
+	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
+		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
+	}
+
+	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 2)
+	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
+
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+
+	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
+		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
+	}
+
+	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 26)
+	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
+
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+
+	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
+		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
+	}
+}
+
+func TestReactorValidatorSetChanges(t *testing.T) {
+	nPeers := 7
+	nVals := 4
+	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentDummy)
+
+	logger := log.TestingLogger()
+
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nPeers)
+	defer stopConsensusNet(logger, reactors, eventBuses)
+
+	// map of active validators
+	activeVals := make(map[string]struct{})
+	for i := 0; i < nVals; i++ {
+		activeVals[string(css[i].privValidator.GetAddress())] = struct{}{}
+	}
+
+	// wait till everyone makes block 1
+	timeoutWaitGroup(t, nPeers, func(wg *sync.WaitGroup, j int) {
+		<-eventChans[j]
+		wg.Done()
+	}, css)
+
+	//---------------------------------------------------------------------------
+	logger.Info("---------------------------- Testing adding one validator")
+
+	newValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
+	newValidatorTx1 := dummy.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), testMinPower)
+
+	// wait till everyone makes block 2
+	// ensure the commit includes all validators
+	// send newValTx to change vals in block 3
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
+
+	// wait till everyone makes block 3.
+	// it includes the commit for block 2, which is by the original validator set
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
+
+	// wait till everyone makes block 4.
+	// it includes the commit for block 3, which is by the original validator set
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+
+	// the commits for block 4 should be with the updated validator set
+	activeVals[string(newValidatorPubKey1.Address())] = struct{}{}
+
+	// wait till everyone makes block 5
+	// it includes the commit for block 4, which should have the updated validator set
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+
+	//---------------------------------------------------------------------------
+	logger.Info("---------------------------- Testing changing the voting power of one validator")
+
+	updateValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
+	updateValidatorTx1 := dummy.MakeValSetChangeTx(updateValidatorPubKey1.Bytes(), 25)
+	previousTotalVotingPower := css[nVals].GetRoundState().LastValidators.TotalVotingPower()
+
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+
+	if css[nVals].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
+		t.Errorf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[nVals].GetRoundState().LastValidators.TotalVotingPower())
+	}
+
+	//---------------------------------------------------------------------------
+	logger.Info("---------------------------- Testing adding two validators at once")
+
+	newValidatorPubKey2 := css[nVals+1].privValidator.GetPubKey()
+	newValidatorTx2 := dummy.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), testMinPower)
+
+	newValidatorPubKey3 := css[nVals+2].privValidator.GetPubKey()
+	newValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), testMinPower)
+
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	activeVals[string(newValidatorPubKey2.Address())] = struct{}{}
+	activeVals[string(newValidatorPubKey3.Address())] = struct{}{}
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+
+	//---------------------------------------------------------------------------
+	logger.Info("---------------------------- Testing removing two validators at once")
+
+	removeValidatorTx2 := dummy.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), 0)
+	removeValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), 0)
+
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
+	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	delete(activeVals, string(newValidatorPubKey2.Address()))
+	delete(activeVals, string(newValidatorPubKey3.Address()))
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+}
+
+// Check we can make blocks with skip_timeout_commit=false
+func TestReactorWithTimeoutCommit(t *testing.T) {
+	N := 4
+	css := randConsensusNet(N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newCounter)
+	// override default SkipTimeoutCommit == true for tests
+	for i := 0; i < N; i++ {
+		css[i].config.SkipTimeoutCommit = false
+	}
+
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N-1)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
+
+	// wait till everyone makes the first new block
+	timeoutWaitGroup(t, N-1, func(wg *sync.WaitGroup, j int) {
+		<-eventChans[j]
+		wg.Done()
+	}, css)
+}
+
+func waitForAndValidateBlock(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
+		defer wg.Done()
+
+		css[j].Logger.Debug("waitForAndValidateBlock")
+		newBlockI, ok := <-eventChans[j]
+		if !ok {
+			return
+		}
+		newBlock := newBlockI.(types.TMEventData).Unwrap().(types.EventDataNewBlock).Block
+		css[j].Logger.Debug("waitForAndValidateBlock: Got block", "height", newBlock.Height)
+		err := validateBlock(newBlock, activeVals)
+		assert.Nil(t, err)
+		for _, tx := range txs {
+			css[j].mempool.CheckTx(tx, nil)
+			assert.Nil(t, err)
+		}
+	}, css)
+}
+
+func waitForAndValidateBlockWithTx(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
+		defer wg.Done()
+		ntxs := 0
+	BLOCK_TX_LOOP:
+		for {
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx", "ntxs", ntxs)
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock := newBlockI.(types.TMEventData).Unwrap().(types.EventDataNewBlock).Block
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx: Got block", "height", newBlock.Height)
+			err := validateBlock(newBlock, activeVals)
+			assert.Nil(t, err)
+
+			// check that txs match the txs we're waiting for.
+			// note they could be spread over multiple blocks,
+			// but they should be in order.
+			for _, tx := range newBlock.Data.Txs {
+				assert.EqualValues(t, txs[ntxs], tx)
+				ntxs += 1
+			}
+
+			if ntxs == len(txs) {
+				break BLOCK_TX_LOOP
+			}
+		}
+
+	}, css)
+}
+
+func waitForBlockWithUpdatedValsAndValidateIt(t *testing.T, n int, updatedVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState) {
+	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
+		defer wg.Done()
+
+		var newBlock *types.Block
+	LOOP:
+		for {
+			css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt")
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock = newBlockI.(types.TMEventData).Unwrap().(types.EventDataNewBlock).Block
+			if newBlock.LastCommit.Size() == len(updatedVals) {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block", "height", newBlock.Height)
+				break LOOP
+			} else {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block with no new validators. Skipping", "height", newBlock.Height)
+			}
+		}
+
+		err := validateBlock(newBlock, updatedVals)
+		assert.Nil(t, err)
+	}, css)
+}
+
+// expects high synchrony!
+func validateBlock(block *types.Block, activeVals map[string]struct{}) error {
+	if block.LastCommit.Size() != len(activeVals) {
+		return fmt.Errorf("Commit size doesn't match number of active validators. Got %d, expected %d", block.LastCommit.Size(), len(activeVals))
+	}
+
+	for _, vote := range block.LastCommit.Precommits {
+		if _, ok := activeVals[string(vote.ValidatorAddress)]; !ok {
+			return fmt.Errorf("Found vote for unactive validator %X", vote.ValidatorAddress)
+		}
+	}
+	return nil
+}
+
+func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*ConsensusState) {
+	wg := new(sync.WaitGroup)
+	wg.Add(n)
+	for i := 0; i < n; i++ {
+		go f(wg, i)
+	}
+
+	done := make(chan struct{})
+	go func() {
+		wg.Wait()
+		close(done)
+	}()
+
+	// we're running many nodes in-process, possibly in in a virtual machine,
+	// and spewing debug messages - making a block could take a while,
+	timeout := time.Second * 300
+
+	select {
+	case <-done:
+	case <-time.After(timeout):
+		for i, cs := range css {
+			t.Log("#################")
+			t.Log("Validator", i)
+			t.Log(cs.GetRoundState())
+			t.Log("")
+		}
+		pprof.Lookup("goroutine").WriteTo(os.Stdout, 1)
+		panic("Timed out waiting for all validators to commit a block")
+	}
+}

consensus/replay.go

@@ -1,39 +1,52 @@
 package consensus
 
 import (
-	"bufio"
-	"errors"
+	"bytes"
 	"fmt"
+	"hash/crc32"
 	"io"
-	"os"
 	"reflect"
-	"strconv"
-	"strings"
+	//"strconv"
+	//"strings"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-wire"
+	abci "github.com/tendermint/abci/types"
+	//auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
 
+	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/version"
 )
 
-// unmarshal and apply a single message to the consensus state
+var crc32c = crc32.MakeTable(crc32.Castagnoli)
+
+// Functionality to replay blocks and messages on recovery from a crash.
+// There are two general failure scenarios: failure during consensus, and failure while applying the block.
+// The former is handled by the WAL, the latter by the proxyApp Handshake on restart,
+// which ultimately hands off the work to the WAL.
+
+//-----------------------------------------
+// recover from failure during consensus
+// by replaying messages from the WAL
+
+// Unmarshal and apply a single message to the consensus state
 // as if it were received in receiveRoutine
+// Lines that start with "#" are ignored.
 // NOTE: receiveRoutine should not be running
-func (cs *ConsensusState) readReplayMessage(msgBytes []byte, newStepCh chan interface{}) error {
-	var err error
-	var msg ConsensusLogMessage
-	wire.ReadJSON(&msg, msgBytes, &err)
-	if err != nil {
-		fmt.Println("MsgBytes:", msgBytes, string(msgBytes))
-		return fmt.Errorf("Error reading json data: %v", err)
+func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan interface{}) error {
+	// skip meta messages
+	if _, ok := msg.Msg.(EndHeightMessage); ok {
+		return nil
 	}
 
 	// for logging
 	switch m := msg.Msg.(type) {
 	case types.EventDataRoundState:
-		log.Notice("Replay: New Step", "height", m.Height, "round", m.Round, "step", m.Step)
+		cs.Logger.Info("Replay: New Step", "height", m.Height, "round", m.Round, "step", m.Step)
 		// these are playback checks
 		ticker := time.After(time.Second * 2)
 		if newStepCh != nil {
@@ -55,306 +68,360 @@ func (cs *ConsensusState) readReplayMessage(msgBytes []byte, newStepCh chan inte
 		switch msg := m.Msg.(type) {
 		case *ProposalMessage:
 			p := msg.Proposal
-			log.Notice("Replay: Proposal", "height", p.Height, "round", p.Round, "header",
+			cs.Logger.Info("Replay: Proposal", "height", p.Height, "round", p.Round, "header",
 				p.BlockPartsHeader, "pol", p.POLRound, "peer", peerKey)
 		case *BlockPartMessage:
-			log.Notice("Replay: BlockPart", "height", msg.Height, "round", msg.Round, "peer", peerKey)
+			cs.Logger.Info("Replay: BlockPart", "height", msg.Height, "round", msg.Round, "peer", peerKey)
 		case *VoteMessage:
 			v := msg.Vote
-			log.Notice("Replay: Vote", "height", v.Height, "round", v.Round, "type", v.Type,
-				"hash", v.BlockHash, "header", v.BlockPartsHeader, "peer", peerKey)
+			cs.Logger.Info("Replay: Vote", "height", v.Height, "round", v.Round, "type", v.Type,
+				"blockID", v.BlockID, "peer", peerKey)
 		}
 
-		cs.handleMsg(m, cs.RoundState)
+		cs.handleMsg(m)
 	case timeoutInfo:
-		log.Notice("Replay: Timeout", "height", m.Height, "round", m.Round, "step", m.Step, "dur", m.Duration)
+		cs.Logger.Info("Replay: Timeout", "height", m.Height, "round", m.Round, "step", m.Step, "dur", m.Duration)
 		cs.handleTimeout(m, cs.RoundState)
 	default:
-		return fmt.Errorf("Replay: Unknown ConsensusLogMessage type: %v", reflect.TypeOf(msg.Msg))
+		return fmt.Errorf("Replay: Unknown TimedWALMessage type: %v", reflect.TypeOf(msg.Msg))
 	}
 	return nil
 }
 
 // replay only those messages since the last block.
 // timeoutRoutine should run concurrently to read off tickChan
-func (cs *ConsensusState) catchupReplay(height int) error {
-	if !cs.wal.Exists() {
-		return nil
-	}
-
+func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 	// set replayMode
 	cs.replayMode = true
 	defer func() { cs.replayMode = false }()
 
-	// starting from end of file,
-	// read messages until a new height is found
-	nLines, err := cs.wal.SeekFromEnd(func(lineBytes []byte) bool {
-		var err error
-		var msg ConsensusLogMessage
-		wire.ReadJSON(&msg, lineBytes, &err)
-		if err != nil {
-			panic(Fmt("Failed to read cs_msg_log json: %v", err))
-		}
-		m, ok := msg.Msg.(types.EventDataRoundState)
-		if ok && m.Step == RoundStepNewHeight.String() {
-			// TODO: ensure the height matches
-			return true
-		}
-		return false
-	})
-
+	// Ensure that ENDHEIGHT for this height doesn't exist.
+	// NOTE: This is just a sanity check. As far as we know things work fine
+	// without it, and Handshake could reuse ConsensusState if it weren't for
+	// this check (since we can crash after writing ENDHEIGHT).
+	//
+	// Ignore data corruption errors since this is a sanity check.
+	gr, found, err := cs.wal.SearchForEndHeight(csHeight, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
 	if err != nil {
 		return err
 	}
-
-	var beginning bool // if we had to go back to the beginning
-	if c, _ := cs.wal.fp.Seek(0, 1); c == 0 {
-		beginning = true
+	if gr != nil {
+		if err := gr.Close(); err != nil {
+			return err
+		}
+	}
+	if found {
+		return fmt.Errorf("WAL should not contain #ENDHEIGHT %d.", csHeight)
 	}
 
-	log.Notice("Catchup by replaying consensus messages", "n", nLines)
+	// Search for last height marker
+	//
+	// Ignore data corruption errors in previous heights because we only care about last height
+	gr, found, err = cs.wal.SearchForEndHeight(csHeight-1, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
+	if err == io.EOF {
+		cs.Logger.Error("Replay: wal.group.Search returned EOF", "#ENDHEIGHT", csHeight-1)
+	} else if err != nil {
+		return err
+	}
+	if !found {
+		return fmt.Errorf("Cannot replay height %d. WAL does not contain #ENDHEIGHT for %d.", csHeight, csHeight-1)
+	}
+	defer gr.Close() // nolint: errcheck
 
-	// now we can replay the latest nLines on consensus state
-	// note we can't use scan because we've already been reading from the file
-	reader := bufio.NewReader(cs.wal.fp)
-	for i := 0; i < nLines; i++ {
-		msgBytes, err := reader.ReadBytes('\n')
+	cs.Logger.Info("Catchup by replaying consensus messages", "height", csHeight)
+
+	var msg *TimedWALMessage
+	dec := WALDecoder{gr}
+
+	for {
+		msg, err = dec.Decode()
 		if err == io.EOF {
 			break
+		} else if IsDataCorruptionError(err) {
+			cs.Logger.Debug("data has been corrupted in last height of consensus WAL", "err", err, "height", csHeight)
+			panic(fmt.Sprintf("data has been corrupted (%v) in last height %d of consensus WAL", err, csHeight))
 		} else if err != nil {
 			return err
-		} else if len(msgBytes) == 0 {
-			continue
-		} else if len(msgBytes) == 1 && msgBytes[0] == '\n' {
-			continue
-		}
-		// the first msg is the NewHeight event (if we're not at the beginning), so we can ignore it
-		if !beginning && i == 1 {
-			continue
 		}
 
 		// NOTE: since the priv key is set when the msgs are received
 		// it will attempt to eg double sign but we can just ignore it
 		// since the votes will be replayed and we'll get to the next step
-		if err := cs.readReplayMessage(msgBytes, nil); err != nil {
+		if err := cs.readReplayMessage(msg, nil); err != nil {
 			return err
 		}
 	}
-	log.Notice("Done catchup replay")
+	cs.Logger.Info("Replay: Done")
 	return nil
 }
 
-//--------------------------------------------------------
-// replay messages interactively or all at once
+//--------------------------------------------------------------------------------
 
-// Interactive playback
-func (cs ConsensusState) ReplayConsole(file string) error {
-	return cs.replay(file, true)
+// Parses marker lines of the form:
+// #ENDHEIGHT: 12345
+/*
+func makeHeightSearchFunc(height int64) auto.SearchFunc {
+	return func(line string) (int, error) {
+		line = strings.TrimRight(line, "\n")
+		parts := strings.Split(line, " ")
+		if len(parts) != 2 {
+			return -1, errors.New("Line did not have 2 parts")
+		}
+		i, err := strconv.Atoi(parts[1])
+		if err != nil {
+			return -1, errors.New("Failed to parse INFO: " + err.Error())
+		}
+		if height < i {
+			return 1, nil
+		} else if height == i {
+			return 0, nil
+		} else {
+			return -1, nil
+		}
+	}
+}*/
+
+//----------------------------------------------
+// Recover from failure during block processing
+// by handshaking with the app to figure out where
+// we were last and using the WAL to recover there
+
+type Handshaker struct {
+	stateDB      dbm.DB
+	initialState sm.State
+	store        types.BlockStore
+	logger       log.Logger
+
+	nBlocks int // number of blocks applied to the state
 }
 
-// Full playback, with tests
-func (cs ConsensusState) ReplayMessages(file string) error {
-	return cs.replay(file, false)
+func NewHandshaker(stateDB dbm.DB, state sm.State, store types.BlockStore) *Handshaker {
+	return &Handshaker{stateDB, state, store, log.NewNopLogger(), 0}
 }
 
-// replay all msgs or start the console
-func (cs *ConsensusState) replay(file string, console bool) error {
-	if cs.IsRunning() {
-		return errors.New("cs is already running, cannot replay")
-	}
-	if cs.wal != nil {
-		return errors.New("cs wal is open, cannot replay")
-	}
+func (h *Handshaker) SetLogger(l log.Logger) {
+	h.logger = l
+}
 
-	cs.startForReplay()
+func (h *Handshaker) NBlocks() int {
+	return h.nBlocks
+}
 
-	// ensure all new step events are regenerated as expected
-	newStepCh := subscribeToEvent(cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
-
-	// just open the file for reading, no need to use wal
-	fp, err := os.OpenFile(file, os.O_RDONLY, 0666)
+// TODO: retry the handshake/replay if it fails ?
+func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
+	// handshake is done via info request on the query conn
+	res, err := proxyApp.Query().InfoSync(abci.RequestInfo{version.Version})
 	if err != nil {
-		return err
+		return fmt.Errorf("Error calling Info: %v", err)
 	}
 
-	pb := newPlayback(file, fp, cs, cs.state.Copy())
-	defer pb.fp.Close()
-
-	var nextN int // apply N msgs in a row
-	for pb.scanner.Scan() {
-		if nextN == 0 && console {
-			nextN = pb.replayConsoleLoop()
-		}
-
-		if err := pb.cs.readReplayMessage(pb.scanner.Bytes(), newStepCh); err != nil {
-			return err
-		}
-
-		if nextN > 0 {
-			nextN -= 1
-		}
-		pb.count += 1
+	blockHeight := int64(res.LastBlockHeight)
+	if blockHeight < 0 {
+		return fmt.Errorf("Got a negative last block height (%d) from the app", blockHeight)
 	}
-	return nil
-}
+	appHash := res.LastBlockAppHash
 
-//------------------------------------------------
-// playback manager
+	h.logger.Info("ABCI Handshake", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
 
-type playback struct {
-	cs *ConsensusState
+	// TODO: check version
 
-	fp      *os.File
-	scanner *bufio.Scanner
-	count   int // how many lines/msgs into the file are we
-
-	// replays can be reset to beginning
-	fileName     string    // so we can close/reopen the file
-	genesisState *sm.State // so the replay session knows where to restart from
-}
-
-func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState *sm.State) *playback {
-	return &playback{
-		cs:           cs,
-		fp:           fp,
-		fileName:     fileName,
-		genesisState: genState,
-		scanner:      bufio.NewScanner(fp),
-	}
-}
-
-// go back count steps by resetting the state and running (pb.count - count) steps
-func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
-
-	pb.cs.Stop()
-
-	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.proxyAppConn, pb.cs.blockStore, pb.cs.mempool)
-	newCS.SetEventSwitch(pb.cs.evsw)
-	newCS.startForReplay()
-
-	pb.fp.Close()
-	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0666)
+	// replay blocks up to the latest in the blockstore
+	_, err = h.ReplayBlocks(h.initialState, appHash, blockHeight, proxyApp)
 	if err != nil {
-		return err
+		return fmt.Errorf("Error on replay: %v", err)
 	}
-	pb.fp = fp
-	pb.scanner = bufio.NewScanner(fp)
-	count = pb.count - count
-	log.Notice(Fmt("Reseting from %d to %d", pb.count, count))
-	pb.count = 0
-	pb.cs = newCS
-	for i := 0; pb.scanner.Scan() && i < count; i++ {
-		if err := pb.cs.readReplayMessage(pb.scanner.Bytes(), newStepCh); err != nil {
-			return err
+
+	h.logger.Info("Completed ABCI Handshake - Tendermint and App are synced", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
+
+	// TODO: (on restart) replay mempool
+
+	return nil
+}
+
+// Replay all blocks since appBlockHeight and ensure the result matches the current state.
+// Returns the final AppHash or an error
+func (h *Handshaker) ReplayBlocks(state sm.State, appHash []byte, appBlockHeight int64, proxyApp proxy.AppConns) ([]byte, error) {
+
+	storeBlockHeight := h.store.Height()
+	stateBlockHeight := state.LastBlockHeight
+	h.logger.Info("ABCI Replay Blocks", "appHeight", appBlockHeight, "storeHeight", storeBlockHeight, "stateHeight", stateBlockHeight)
+
+	// If appBlockHeight == 0 it means that we are at genesis and hence should send InitChain
+	if appBlockHeight == 0 {
+		validators := types.TM2PB.Validators(state.Validators)
+		if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+			return nil, err
 		}
-		pb.count += 1
+	}
+
+	// First handle edge cases and constraints on the storeBlockHeight
+	if storeBlockHeight == 0 {
+		return appHash, checkAppHash(state, appHash)
+
+	} else if storeBlockHeight < appBlockHeight {
+		// the app should never be ahead of the store (but this is under app's control)
+		return appHash, sm.ErrAppBlockHeightTooHigh{storeBlockHeight, appBlockHeight}
+
+	} else if storeBlockHeight < stateBlockHeight {
+		// the state should never be ahead of the store (this is under tendermint's control)
+		cmn.PanicSanity(cmn.Fmt("StateBlockHeight (%d) > StoreBlockHeight (%d)", stateBlockHeight, storeBlockHeight))
+
+	} else if storeBlockHeight > stateBlockHeight+1 {
+		// store should be at most one ahead of the state (this is under tendermint's control)
+		cmn.PanicSanity(cmn.Fmt("StoreBlockHeight (%d) > StateBlockHeight + 1 (%d)", storeBlockHeight, stateBlockHeight+1))
+	}
+
+	var err error
+	// Now either store is equal to state, or one ahead.
+	// For each, consider all cases of where the app could be, given app <= store
+	if storeBlockHeight == stateBlockHeight {
+		// Tendermint ran Commit and saved the state.
+		// Either the app is asking for replay, or we're all synced up.
+		if appBlockHeight < storeBlockHeight {
+			// the app is behind, so replay blocks, but no need to go through WAL (state is already synced to store)
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, false)
+
+		} else if appBlockHeight == storeBlockHeight {
+			// We're good!
+			return appHash, checkAppHash(state, appHash)
+		}
+
+	} else if storeBlockHeight == stateBlockHeight+1 {
+		// We saved the block in the store but haven't updated the state,
+		// so we'll need to replay a block using the WAL.
+		if appBlockHeight < stateBlockHeight {
+			// the app is further behind than it should be, so replay blocks
+			// but leave the last block to go through the WAL
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, true)
+
+		} else if appBlockHeight == stateBlockHeight {
+			// We haven't run Commit (both the state and app are one block behind),
+			// so replayBlock with the real app.
+			// NOTE: We could instead use the cs.WAL on cs.Start,
+			// but we'd have to allow the WAL to replay a block that wrote it's ENDHEIGHT
+			h.logger.Info("Replay last block using real app")
+			state, err = h.replayBlock(state, storeBlockHeight, proxyApp.Consensus())
+			return state.AppHash, err
+
+		} else if appBlockHeight == storeBlockHeight {
+			// We ran Commit, but didn't save the state, so replayBlock with mock app
+			abciResponses, err := sm.LoadABCIResponses(h.stateDB, storeBlockHeight)
+			if err != nil {
+				return nil, err
+			}
+			mockApp := newMockProxyApp(appHash, abciResponses)
+			h.logger.Info("Replay last block using mock app")
+			state, err = h.replayBlock(state, storeBlockHeight, mockApp)
+			return state.AppHash, err
+		}
+
+	}
+
+	cmn.PanicSanity("Should never happen")
+	return nil, nil
+}
+
+func (h *Handshaker) replayBlocks(state sm.State, proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int64, mutateState bool) ([]byte, error) {
+	// App is further behind than it should be, so we need to replay blocks.
+	// We replay all blocks from appBlockHeight+1.
+	//
+	// Note that we don't have an old version of the state,
+	// so we by-pass state validation/mutation using sm.ExecCommitBlock.
+	// This also means we won't be saving validator sets if they change during this period.
+	// TODO: Load the historical information to fix this and just use state.ApplyBlock
+	//
+	// If mutateState == true, the final block is replayed with h.replayBlock()
+
+	var appHash []byte
+	var err error
+	finalBlock := storeBlockHeight
+	if mutateState {
+		finalBlock -= 1
+	}
+	for i := appBlockHeight + 1; i <= finalBlock; i++ {
+		h.logger.Info("Applying block", "height", i)
+		block := h.store.LoadBlock(i)
+		appHash, err = sm.ExecCommitBlock(proxyApp.Consensus(), block, h.logger)
+		if err != nil {
+			return nil, err
+		}
+
+		h.nBlocks += 1
+	}
+
+	if mutateState {
+		// sync the final block
+		state, err = h.replayBlock(state, storeBlockHeight, proxyApp.Consensus())
+		if err != nil {
+			return nil, err
+		}
+		appHash = state.AppHash
+	}
+
+	return appHash, checkAppHash(state, appHash)
+}
+
+// ApplyBlock on the proxyApp with the last block.
+func (h *Handshaker) replayBlock(state sm.State, height int64, proxyApp proxy.AppConnConsensus) (sm.State, error) {
+	block := h.store.LoadBlock(height)
+	meta := h.store.LoadBlockMeta(height)
+
+	blockExec := sm.NewBlockExecutor(h.stateDB, h.logger, proxyApp, types.MockMempool{}, types.MockEvidencePool{})
+
+	var err error
+	state, err = blockExec.ApplyBlock(state, meta.BlockID, block)
+	if err != nil {
+		return sm.State{}, err
+	}
+
+	h.nBlocks += 1
+
+	return state, nil
+}
+
+func checkAppHash(state sm.State, appHash []byte) error {
+	if !bytes.Equal(state.AppHash, appHash) {
+		panic(fmt.Errorf("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, state.AppHash).Error())
 	}
 	return nil
 }
 
-func (cs *ConsensusState) startForReplay() {
-	// don't want to start full cs
-	cs.BaseService.OnStart()
+//--------------------------------------------------------------------------------
+// mockProxyApp uses ABCIResponses to give the right results
+// Useful because we don't want to call Commit() twice for the same block on the real app.
 
-	// since we replay tocks we just ignore ticks
-	go func() {
-		for {
-			select {
-			case <-cs.tickChan:
-			case <-cs.Quit:
-				return
-			}
-		}
-	}()
-}
-
-// console function for parsing input and running commands
-func (pb *playback) replayConsoleLoop() int {
-	for {
-		fmt.Printf("> ")
-		bufReader := bufio.NewReader(os.Stdin)
-		line, more, err := bufReader.ReadLine()
-		if more {
-			Exit("input is too long")
-		} else if err != nil {
-			Exit(err.Error())
-		}
-
-		tokens := strings.Split(string(line), " ")
-		if len(tokens) == 0 {
-			continue
-		}
-
-		switch tokens[0] {
-		case "next":
-			// "next" -> replay next message
-			// "next N" -> replay next N messages
-
-			if len(tokens) == 1 {
-				return 0
-			} else {
-				i, err := strconv.Atoi(tokens[1])
-				if err != nil {
-					fmt.Println("next takes an integer argument")
-				} else {
-					return i
-				}
-			}
-
-		case "back":
-			// "back" -> go back one message
-			// "back N" -> go back N messages
-
-			// NOTE: "back" is not supported in the state machine design,
-			// so we restart and replay up to
-
-			// ensure all new step events are regenerated as expected
-			newStepCh := subscribeToEvent(pb.cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
-			if len(tokens) == 1 {
-				pb.replayReset(1, newStepCh)
-			} else {
-				i, err := strconv.Atoi(tokens[1])
-				if err != nil {
-					fmt.Println("back takes an integer argument")
-				} else if i > pb.count {
-					fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
-				} else {
-					pb.replayReset(i, newStepCh)
-				}
-			}
-
-		case "rs":
-			// "rs" -> print entire round state
-			// "rs short" -> print height/round/step
-			// "rs <field>" -> print another field of the round state
-
-			rs := pb.cs.RoundState
-			if len(tokens) == 1 {
-				fmt.Println(rs)
-			} else {
-				switch tokens[1] {
-				case "short":
-					fmt.Printf("%v/%v/%v\n", rs.Height, rs.Round, rs.Step)
-				case "validators":
-					fmt.Println(rs.Validators)
-				case "proposal":
-					fmt.Println(rs.Proposal)
-				case "proposal_block":
-					fmt.Printf("%v %v\n", rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort())
-				case "locked_round":
-					fmt.Println(rs.LockedRound)
-				case "locked_block":
-					fmt.Printf("%v %v\n", rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort())
-				case "votes":
-					fmt.Println(rs.Votes.StringIndented("    "))
-
-				default:
-					fmt.Println("Unknown option", tokens[1])
-				}
-			}
-		case "n":
-			fmt.Println(pb.count)
-		}
+func newMockProxyApp(appHash []byte, abciResponses *sm.ABCIResponses) proxy.AppConnConsensus {
+	clientCreator := proxy.NewLocalClientCreator(&mockProxyApp{
+		appHash:       appHash,
+		abciResponses: abciResponses,
+	})
+	cli, _ := clientCreator.NewABCIClient()
+	err := cli.Start()
+	if err != nil {
+		panic(err)
 	}
-	return 0
+	return proxy.NewAppConnConsensus(cli)
+}
+
+type mockProxyApp struct {
+	abci.BaseApplication
+
+	appHash       []byte
+	txCount       int
+	abciResponses *sm.ABCIResponses
+}
+
+func (mock *mockProxyApp) DeliverTx(tx []byte) abci.ResponseDeliverTx {
+	r := mock.abciResponses.DeliverTx[mock.txCount]
+	mock.txCount += 1
+	return *r
+}
+
+func (mock *mockProxyApp) EndBlock(req abci.RequestEndBlock) abci.ResponseEndBlock {
+	mock.txCount = 0
+	return *mock.abciResponses.EndBlock
+}
+
+func (mock *mockProxyApp) Commit() abci.ResponseCommit {
+	return abci.ResponseCommit{Code: abci.CodeTypeOK, Data: mock.appHash}
 }

consensus/replay_file.go

@@ -0,0 +1,315 @@
+package consensus
+
+import (
+	"bufio"
+	"context"
+	"fmt"
+	"io"
+	"os"
+	"strconv"
+	"strings"
+
+	"github.com/pkg/errors"
+
+	bc "github.com/tendermint/tendermint/blockchain"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+const (
+	// event bus subscriber
+	subscriber = "replay-file"
+)
+
+//--------------------------------------------------------
+// replay messages interactively or all at once
+
+func RunReplayFile(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig, console bool) {
+	consensusState := newConsensusStateForReplay(config, csConfig)
+
+	if err := consensusState.ReplayFile(csConfig.WalFile(), console); err != nil {
+		cmn.Exit(cmn.Fmt("Error during consensus replay: %v", err))
+	}
+}
+
+// Replay msgs in file or start the console
+func (cs *ConsensusState) ReplayFile(file string, console bool) error {
+
+	if cs.IsRunning() {
+		return errors.New("cs is already running, cannot replay")
+	}
+	if cs.wal != nil {
+		return errors.New("cs wal is open, cannot replay")
+	}
+
+	cs.startForReplay()
+
+	// ensure all new step events are regenerated as expected
+	newStepCh := make(chan interface{}, 1)
+
+	ctx := context.Background()
+	err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+	if err != nil {
+		return errors.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
+	}
+	defer cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
+
+	// just open the file for reading, no need to use wal
+	fp, err := os.OpenFile(file, os.O_RDONLY, 0600)
+	if err != nil {
+		return err
+	}
+
+	pb := newPlayback(file, fp, cs, cs.state.Copy())
+	defer pb.fp.Close() // nolint: errcheck
+
+	var nextN int // apply N msgs in a row
+	var msg *TimedWALMessage
+	for {
+		if nextN == 0 && console {
+			nextN = pb.replayConsoleLoop()
+		}
+
+		msg, err = pb.dec.Decode()
+		if err == io.EOF {
+			return nil
+		} else if err != nil {
+			return err
+		}
+
+		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
+			return err
+		}
+
+		if nextN > 0 {
+			nextN -= 1
+		}
+		pb.count += 1
+	}
+	return nil
+}
+
+//------------------------------------------------
+// playback manager
+
+type playback struct {
+	cs *ConsensusState
+
+	fp    *os.File
+	dec   *WALDecoder
+	count int // how many lines/msgs into the file are we
+
+	// replays can be reset to beginning
+	fileName     string   // so we can close/reopen the file
+	genesisState sm.State // so the replay session knows where to restart from
+}
+
+func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState sm.State) *playback {
+	return &playback{
+		cs:           cs,
+		fp:           fp,
+		fileName:     fileName,
+		genesisState: genState,
+		dec:          NewWALDecoder(fp),
+	}
+}
+
+// go back count steps by resetting the state and running (pb.count - count) steps
+func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
+	pb.cs.Stop()
+	pb.cs.Wait()
+
+	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
+		pb.cs.blockStore, pb.cs.mempool, pb.cs.evpool)
+	newCS.SetEventBus(pb.cs.eventBus)
+	newCS.startForReplay()
+
+	if err := pb.fp.Close(); err != nil {
+		return err
+	}
+	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0600)
+	if err != nil {
+		return err
+	}
+	pb.fp = fp
+	pb.dec = NewWALDecoder(fp)
+	count = pb.count - count
+	fmt.Printf("Reseting from %d to %d\n", pb.count, count)
+	pb.count = 0
+	pb.cs = newCS
+	var msg *TimedWALMessage
+	for i := 0; i < count; i++ {
+		msg, err = pb.dec.Decode()
+		if err == io.EOF {
+			return nil
+		} else if err != nil {
+			return err
+		}
+		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
+			return err
+		}
+		pb.count += 1
+	}
+	return nil
+}
+
+func (cs *ConsensusState) startForReplay() {
+	cs.Logger.Error("Replay commands are disabled until someone updates them and writes tests")
+	/* TODO:!
+	// since we replay tocks we just ignore ticks
+		go func() {
+			for {
+				select {
+				case <-cs.tickChan:
+				case <-cs.Quit:
+					return
+				}
+			}
+		}()*/
+}
+
+// console function for parsing input and running commands
+func (pb *playback) replayConsoleLoop() int {
+	for {
+		fmt.Printf("> ")
+		bufReader := bufio.NewReader(os.Stdin)
+		line, more, err := bufReader.ReadLine()
+		if more {
+			cmn.Exit("input is too long")
+		} else if err != nil {
+			cmn.Exit(err.Error())
+		}
+
+		tokens := strings.Split(string(line), " ")
+		if len(tokens) == 0 {
+			continue
+		}
+
+		switch tokens[0] {
+		case "next":
+			// "next" -> replay next message
+			// "next N" -> replay next N messages
+
+			if len(tokens) == 1 {
+				return 0
+			} else {
+				i, err := strconv.Atoi(tokens[1])
+				if err != nil {
+					fmt.Println("next takes an integer argument")
+				} else {
+					return i
+				}
+			}
+
+		case "back":
+			// "back" -> go back one message
+			// "back N" -> go back N messages
+
+			// NOTE: "back" is not supported in the state machine design,
+			// so we restart and replay up to
+
+			ctx := context.Background()
+			// ensure all new step events are regenerated as expected
+			newStepCh := make(chan interface{}, 1)
+
+			err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+			if err != nil {
+				cmn.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
+			}
+			defer pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
+
+			if len(tokens) == 1 {
+				if err := pb.replayReset(1, newStepCh); err != nil {
+					pb.cs.Logger.Error("Replay reset error", "err", err)
+				}
+			} else {
+				i, err := strconv.Atoi(tokens[1])
+				if err != nil {
+					fmt.Println("back takes an integer argument")
+				} else if i > pb.count {
+					fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
+				} else {
+					if err := pb.replayReset(i, newStepCh); err != nil {
+						pb.cs.Logger.Error("Replay reset error", "err", err)
+					}
+				}
+			}
+
+		case "rs":
+			// "rs" -> print entire round state
+			// "rs short" -> print height/round/step
+			// "rs <field>" -> print another field of the round state
+
+			rs := pb.cs.RoundState
+			if len(tokens) == 1 {
+				fmt.Println(rs)
+			} else {
+				switch tokens[1] {
+				case "short":
+					fmt.Printf("%v/%v/%v\n", rs.Height, rs.Round, rs.Step)
+				case "validators":
+					fmt.Println(rs.Validators)
+				case "proposal":
+					fmt.Println(rs.Proposal)
+				case "proposal_block":
+					fmt.Printf("%v %v\n", rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort())
+				case "locked_round":
+					fmt.Println(rs.LockedRound)
+				case "locked_block":
+					fmt.Printf("%v %v\n", rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort())
+				case "votes":
+					fmt.Println(rs.Votes.StringIndented("    "))
+
+				default:
+					fmt.Println("Unknown option", tokens[1])
+				}
+			}
+		case "n":
+			fmt.Println(pb.count)
+		}
+	}
+	return 0
+}
+
+//--------------------------------------------------------------------------------
+
+// convenience for replay mode
+func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig) *ConsensusState {
+	// Get BlockStore
+	blockStoreDB := dbm.NewDB("blockstore", config.DBBackend, config.DBDir())
+	blockStore := bc.NewBlockStore(blockStoreDB)
+
+	// Get State
+	stateDB := dbm.NewDB("state", config.DBBackend, config.DBDir())
+	state, err := sm.MakeGenesisStateFromFile(config.GenesisFile())
+	if err != nil {
+		cmn.Exit(err.Error())
+	}
+
+	// Create proxyAppConn connection (consensus, mempool, query)
+	clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
+	proxyApp := proxy.NewAppConns(clientCreator, NewHandshaker(stateDB, state, blockStore))
+	err = proxyApp.Start()
+	if err != nil {
+		cmn.Exit(cmn.Fmt("Error starting proxy app conns: %v", err))
+	}
+
+	eventBus := types.NewEventBus()
+	if err := eventBus.Start(); err != nil {
+		cmn.Exit(cmn.Fmt("Failed to start event bus: %v", err))
+	}
+
+	mempool, evpool := types.MockMempool{}, types.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+
+	consensusState := NewConsensusState(csConfig, state.Copy(), blockExec,
+		blockStore, mempool, evpool)
+
+	consensusState.SetEventBus(eventBus)
+	return consensusState
+}

consensus/replay_test.go

@@ -1,203 +1,627 @@
 package consensus
 
 import (
+	"bytes"
+	"context"
+	"errors"
 	"fmt"
+	"io"
 	"io/ioutil"
 	"os"
-	"strings"
+	"path"
+	"runtime"
 	"testing"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-events"
-	"github.com/tendermint/go-wire"
+	"github.com/stretchr/testify/require"
+
+	"github.com/tendermint/abci/example/dummy"
+	abci "github.com/tendermint/abci/types"
+	crypto "github.com/tendermint/go-crypto"
+	wire "github.com/tendermint/go-wire"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tmlibs/log"
 )
 
-/*
-	The easiest way to generate this data is to copy ~/.tendermint_test/somedir/* to ~/.tendermint
-	and to run a local node.
-	Be sure to set the db to "leveldb" to create a cswal file in ~/.tendermint/data/cswal.
+var consensusReplayConfig *cfg.Config
 
-	If you need to change the signatures, you can use a script as follows:
-	The privBytes comes from config/tendermint_test/...
-
-	```
-	package main
-
-	import (
-		"encoding/hex"
-		"fmt"
-
-		"github.com/tendermint/go-crypto"
-	)
-
-	func main() {
-		signBytes, err := hex.DecodeString("7B22636861696E5F6964223A2274656E6465726D696E745F74657374222C22766F7465223A7B22626C6F636B5F68617368223A2242453544373939433846353044354645383533364334333932464443384537423342313830373638222C22626C6F636B5F70617274735F686561646572223A506172745365747B543A31204236323237323535464632307D2C22686569676874223A312C22726F756E64223A302C2274797065223A327D7D")
-		if err != nil {
-			panic(err)
-		}
-		privBytes, err := hex.DecodeString("27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8")
-		if err != nil {
-			panic(err)
-		}
-		privKey := crypto.PrivKeyEd25519{}
-		copy(privKey[:], privBytes)
-		signature := privKey.Sign(signBytes)
-		signatureEd25519 := signature.(crypto.SignatureEd25519)
-		fmt.Printf("Signature Bytes: %X\n", signatureEd25519[:])
-	}
-	```
-*/
-
-var testLog = `{"time":"2016-04-03T11:23:54.387Z","msg":[3,{"duration":972835254,"height":1,"round":0,"step":1}]}
-{"time":"2016-04-03T11:23:54.388Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPropose"}]}
-{"time":"2016-04-03T11:23:54.388Z","msg":[2,{"msg":[17,{"Proposal":{"height":1,"round":0,"block_parts_header":{"total":1,"hash":"3BA1E90CB868DA6B4FD7F3589826EC461E9EB4EF"},"pol_round":-1,"signature":"3A2ECD5023B21EC144EC16CFF1B992A4321317B83EEDD8969FDFEA6EB7BF4389F38DDA3E7BB109D63A07491C16277A197B241CF1F05F5E485C59882ECACD9E07"}}],"peer_key":""}]}
-{"time":"2016-04-03T11:23:54.389Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":0,"bytes":"0101010F74656E6465726D696E745F7465737401011441D59F4B718AC00000000000000114C4B01D3810579550997AC5641E759E20D99B51C10001000100","proof":{"aunts":[]}}}],"peer_key":""}]}
-{"time":"2016-04-03T11:23:54.390Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrevote"}]}
-{"time":"2016-04-03T11:23:54.390Z","msg":[2,{"msg":[20,{"ValidatorIndex":0,"Vote":{"height":1,"round":0,"type":1,"block_hash":"4291966B8A9DFBA00AEC7C700F2718E61DF4331D","block_parts_header":{"total":1,"hash":"3BA1E90CB868DA6B4FD7F3589826EC461E9EB4EF"},"signature":"47D2A75A4E2F15DB1F0D1B656AC0637AF9AADDFEB6A156874F6553C73895E5D5DC948DBAEF15E61276C5342D0E638DFCB77C971CD282096EA8735A564A90F008"}}],"peer_key":""}]}
-{"time":"2016-04-03T11:23:54.392Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrecommit"}]}
-{"time":"2016-04-03T11:23:54.392Z","msg":[2,{"msg":[20,{"ValidatorIndex":0,"Vote":{"height":1,"round":0,"type":2,"block_hash":"4291966B8A9DFBA00AEC7C700F2718E61DF4331D","block_parts_header":{"total":1,"hash":"3BA1E90CB868DA6B4FD7F3589826EC461E9EB4EF"},"signature":"39147DA595F08B73CF8C899967C8403B5872FD9042FFA4E239159E0B6C5D9665C9CA81D766EACA2AE658872F94C2FCD1E34BF51859CD5B274DA8512BACE4B50D"}}],"peer_key":""}]}
-`
-
-// map lines in the above wal to privVal step
-var mapPrivValStep = map[int]int8{
-	0: 0,
-	1: 0,
-	2: 1,
-	3: 1,
-	4: 1,
-	5: 2,
-	6: 2,
-	7: 3,
+func init() {
+	consensusReplayConfig = ResetConfig("consensus_replay_test")
 }
 
-func writeWAL(log string) string {
-	fmt.Println("writing", log)
-	// write the needed wal to file
-	f, err := ioutil.TempFile(os.TempDir(), "replay_test_")
-	if err != nil {
-		panic(err)
-	}
+// These tests ensure we can always recover from failure at any part of the consensus process.
+// There are two general failure scenarios: failure during consensus, and failure while applying the block.
+// Only the latter interacts with the app and store,
+// but the former has to deal with restrictions on re-use of priv_validator keys.
+// The `WAL Tests` are for failures during the consensus;
+// the `Handshake Tests` are for failures in applying the block.
+// With the help of the WAL, we can recover from it all!
 
-	_, err = f.WriteString(log)
-	if err != nil {
-		panic(err)
-	}
-	name := f.Name()
-	f.Close()
-	return name
-}
+//------------------------------------------------------------------------------------------
+// WAL Tests
 
-func waitForBlock(newBlockCh chan interface{}) {
-	after := time.After(time.Second * 10)
+// TODO: It would be better to verify explicitly which states we can recover from without the wal
+// and which ones we need the wal for - then we'd also be able to only flush the
+// wal writer when we need to, instead of with every message.
+
+func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
+	logger := log.TestingLogger()
+	state, _ := sm.LoadStateFromDBOrGenesisFile(stateDB, consensusReplayConfig.GenesisFile())
+	privValidator := loadPrivValidator(consensusReplayConfig)
+	cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, dummy.NewDummyApplication(), blockDB)
+	cs.SetLogger(logger)
+
+	bytes, _ := ioutil.ReadFile(cs.config.WalFile())
+	// fmt.Printf("====== WAL: \n\r%s\n", bytes)
+	t.Logf("====== WAL: \n\r%s\n", bytes)
+
+	err := cs.Start()
+	require.NoError(t, err)
+	defer cs.Stop()
+
+	// This is just a signal that we haven't halted; its not something contained
+	// in the WAL itself. Assuming the consensus state is running, replay of any
+	// WAL, including the empty one, should eventually be followed by a new
+	// block, or else something is wrong.
+	newBlockCh := make(chan interface{}, 1)
+	err = cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, newBlockCh)
+	require.NoError(t, err)
 	select {
 	case <-newBlockCh:
-	case <-after:
-		panic("Timed out waiting for new block")
+	case <-time.After(60 * time.Second):
+		t.Fatalf("Timed out waiting for new block (see trace above)")
 	}
 }
 
-func runReplayTest(t *testing.T, cs *ConsensusState, fileName string, newBlockCh chan interface{}) {
-	cs.config.Set("cswal", fileName)
-	cs.Start()
-	// Wait to make a new block.
-	// This is just a signal that we haven't halted; its not something contained in the WAL itself.
-	// Assuming the consensus state is running, replay of any WAL, including the empty one,
-	// should eventually be followed by a new block, or else something is wrong
-	waitForBlock(newBlockCh)
-	cs.Stop()
-}
-
-func setupReplayTest(nLines int, crashAfter bool) (*ConsensusState, chan interface{}, string, string) {
-	fmt.Println("-------------------------------------")
-	log.Notice(Fmt("Starting replay test of %d lines of WAL (crash before write)", nLines))
-
-	lineStep := nLines
-	if crashAfter {
-		lineStep -= 1
-	}
-
-	split := strings.Split(testLog, "\n")
-	lastMsg := split[nLines]
-
-	// we write those lines up to (not including) one with the signature
-	fileName := writeWAL(strings.Join(split[:nLines], "\n") + "\n")
-
-	cs := fixedConsensusState()
-
-	// set the last step according to when we crashed vs the wal
-	cs.privValidator.LastHeight = 1 // first block
-	cs.privValidator.LastStep = mapPrivValStep[lineStep]
-
-	fmt.Println("LAST STEP", cs.privValidator.LastStep)
-
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-
-	return cs, newBlockCh, lastMsg, fileName
-}
-
-//-----------------------------------------------
-// Test the log at every iteration, and set the privVal last step
-// as if the log was written after signing, before the crash
-
-func TestReplayCrashAfterWrite(t *testing.T) {
-	split := strings.Split(testLog, "\n")
-	for i := 0; i < len(split)-1; i++ {
-		cs, newBlockCh, _, f := setupReplayTest(i+1, true)
-		runReplayTest(t, cs, f, newBlockCh)
+func sendTxs(cs *ConsensusState, ctx context.Context) {
+	i := 0
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+			cs.mempool.CheckTx([]byte{byte(i)}, nil)
+			i++
+		}
 	}
 }
 
-//-----------------------------------------------
-// Test the log as if we crashed after signing but before writing.
-// This relies on privValidator.LastSignature being set
+// TestWALCrash uses crashing WAL to test we can recover from any WAL failure.
+func TestWALCrash(t *testing.T) {
+	testCases := []struct {
+		name         string
+		initFn       func(dbm.DB, *ConsensusState, context.Context)
+		heightToStop int64
+	}{
+		{"empty block",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {},
+			1},
+		{"block with a smaller part size",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				// XXX: is there a better way to change BlockPartSizeBytes?
+				cs.state.ConsensusParams.BlockPartSizeBytes = 512
+				sm.SaveState(stateDB, cs.state)
+				go sendTxs(cs, ctx)
+			},
+			1},
+		{"many non-empty blocks",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				go sendTxs(cs, ctx)
+			},
+			3},
+	}
 
-func TestReplayCrashBeforeWritePropose(t *testing.T) {
-	cs, newBlockCh, proposalMsg, f := setupReplayTest(2, false) // propose
-	// Set LastSig
-	var err error
-	var msg ConsensusLogMessage
-	wire.ReadJSON(&msg, []byte(proposalMsg), &err)
-	proposal := msg.Msg.(msgInfo).Msg.(*ProposalMessage)
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			crashWALandCheckLiveness(t, tc.initFn, tc.heightToStop)
+		})
+	}
+}
+
+func crashWALandCheckLiveness(t *testing.T, initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
+	walPaniced := make(chan error)
+	crashingWal := &crashingWAL{panicCh: walPaniced, heightToStop: heightToStop}
+
+	i := 1
+LOOP:
+	for {
+		// fmt.Printf("====== LOOP %d\n", i)
+		t.Logf("====== LOOP %d\n", i)
+
+		// create consensus state from a clean slate
+		logger := log.NewNopLogger()
+		stateDB := dbm.NewMemDB()
+		state, _ := sm.MakeGenesisStateFromFile(consensusReplayConfig.GenesisFile())
+		privValidator := loadPrivValidator(consensusReplayConfig)
+		blockDB := dbm.NewMemDB()
+		cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, dummy.NewDummyApplication(), blockDB)
+		cs.SetLogger(logger)
+
+		// start sending transactions
+		ctx, cancel := context.WithCancel(context.Background())
+		initFn(stateDB, cs, ctx)
+
+		// clean up WAL file from the previous iteration
+		walFile := cs.config.WalFile()
+		os.Remove(walFile)
+
+		// set crashing WAL
+		csWal, err := cs.OpenWAL(walFile)
+		require.NoError(t, err)
+		crashingWal.next = csWal
+		// reset the message counter
+		crashingWal.msgIndex = 1
+		cs.wal = crashingWal
+
+		// start consensus state
+		err = cs.Start()
+		require.NoError(t, err)
+
+		i++
+
+		select {
+		case err := <-walPaniced:
+			t.Logf("WAL paniced: %v", err)
+
+			// make sure we can make blocks after a crash
+			startNewConsensusStateAndWaitForBlock(t, cs.Height, blockDB, stateDB)
+
+			// stop consensus state and transactions sender (initFn)
+			cs.Stop()
+			cancel()
+
+			// if we reached the required height, exit
+			if _, ok := err.(ReachedHeightToStopError); ok {
+				break LOOP
+			}
+		case <-time.After(10 * time.Second):
+			t.Fatal("WAL did not panic for 10 seconds (check the log)")
+		}
+	}
+}
+
+// crashingWAL is a WAL which crashes or rather simulates a crash during Save
+// (before and after). It remembers a message for which we last panicked
+// (lastPanicedForMsgIndex), so we don't panic for it in subsequent iterations.
+type crashingWAL struct {
+	next         WAL
+	panicCh      chan error
+	heightToStop int64
+
+	msgIndex               int // current message index
+	lastPanicedForMsgIndex int // last message for which we panicked
+}
+
+// WALWriteError indicates a WAL crash.
+type WALWriteError struct {
+	msg string
+}
+
+func (e WALWriteError) Error() string {
+	return e.msg
+}
+
+// ReachedHeightToStopError indicates we've reached the required consensus
+// height and may exit.
+type ReachedHeightToStopError struct {
+	height int64
+}
+
+func (e ReachedHeightToStopError) Error() string {
+	return fmt.Sprintf("reached height to stop %d", e.height)
+}
+
+// Save simulate WAL's crashing by sending an error to the panicCh and then
+// exiting the cs.receiveRoutine.
+func (w *crashingWAL) Save(m WALMessage) {
+	if endMsg, ok := m.(EndHeightMessage); ok {
+		if endMsg.Height == w.heightToStop {
+			w.panicCh <- ReachedHeightToStopError{endMsg.Height}
+			runtime.Goexit()
+		} else {
+			w.next.Save(m)
+		}
+		return
+	}
+
+	if w.msgIndex > w.lastPanicedForMsgIndex {
+		w.lastPanicedForMsgIndex = w.msgIndex
+		_, file, line, _ := runtime.Caller(1)
+		w.panicCh <- WALWriteError{fmt.Sprintf("failed to write %T to WAL (fileline: %s:%d)", m, file, line)}
+		runtime.Goexit()
+	} else {
+		w.msgIndex++
+		w.next.Save(m)
+	}
+}
+
+func (w *crashingWAL) Group() *auto.Group { return w.next.Group() }
+func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return w.next.SearchForEndHeight(height, options)
+}
+
+func (w *crashingWAL) Start() error { return w.next.Start() }
+func (w *crashingWAL) Stop() error  { return w.next.Stop() }
+func (w *crashingWAL) Wait()        { w.next.Wait() }
+
+//------------------------------------------------------------------------------------------
+// Handshake Tests
+
+const (
+	NUM_BLOCKS = 6
+)
+
+var (
+	mempool = types.MockMempool{}
+	evpool  = types.MockEvidencePool{}
+)
+
+//---------------------------------------
+// Test handshake/replay
+
+// 0 - all synced up
+// 1 - saved block but app and state are behind
+// 2 - save block and committed but state is behind
+var modes = []uint{0, 1, 2}
+
+// Sync from scratch
+func TestHandshakeReplayAll(t *testing.T) {
+	for _, m := range modes {
+		testHandshakeReplay(t, 0, m)
+	}
+}
+
+// Sync many, not from scratch
+func TestHandshakeReplaySome(t *testing.T) {
+	for _, m := range modes {
+		testHandshakeReplay(t, 1, m)
+	}
+}
+
+// Sync from lagging by one
+func TestHandshakeReplayOne(t *testing.T) {
+	for _, m := range modes {
+		testHandshakeReplay(t, NUM_BLOCKS-1, m)
+	}
+}
+
+// Sync from caught up
+func TestHandshakeReplayNone(t *testing.T) {
+	for _, m := range modes {
+		testHandshakeReplay(t, NUM_BLOCKS, m)
+	}
+}
+
+func tempWALWithData(data []byte) string {
+	walFile, err := ioutil.TempFile("", "wal")
 	if err != nil {
-		t.Fatalf("Error reading json data: %v", err)
+		panic(fmt.Errorf("failed to create temp WAL file: %v", err))
 	}
-	cs.privValidator.LastSignBytes = types.SignBytes(cs.state.ChainID, proposal.Proposal)
-	cs.privValidator.LastSignature = proposal.Proposal.Signature
-	runReplayTest(t, cs, f, newBlockCh)
+	_, err = walFile.Write(data)
+	if err != nil {
+		panic(fmt.Errorf("failed to write to temp WAL file: %v", err))
+	}
+	if err := walFile.Close(); err != nil {
+		panic(fmt.Errorf("failed to close temp WAL file: %v", err))
+	}
+	return walFile.Name()
 }
 
-func TestReplayCrashBeforeWritePrevote(t *testing.T) {
-	cs, newBlockCh, voteMsg, f := setupReplayTest(5, false) // prevote
-	cs.evsw.AddListenerForEvent("tester", types.EventStringCompleteProposal(), func(data events.EventData) {
-		// Set LastSig
-		var err error
-		var msg ConsensusLogMessage
-		wire.ReadJSON(&msg, []byte(voteMsg), &err)
-		vote := msg.Msg.(msgInfo).Msg.(*VoteMessage)
-		if err != nil {
-			t.Fatalf("Error reading json data: %v", err)
-		}
-		cs.privValidator.LastSignBytes = types.SignBytes(cs.state.ChainID, vote.Vote)
-		cs.privValidator.LastSignature = vote.Vote.Signature
-	})
-	runReplayTest(t, cs, f, newBlockCh)
+// Make some blocks. Start a fresh app and apply nBlocks blocks. Then restart the app and sync it up with the remaining blocks
+func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
+	config := ResetConfig("proxy_test_")
+
+	walBody, err := WALWithNBlocks(NUM_BLOCKS)
+	if err != nil {
+		t.Fatal(err)
+	}
+	walFile := tempWALWithData(walBody)
+	config.Consensus.SetWalFile(walFile)
+
+	privVal := types.LoadPrivValidatorFS(config.PrivValidatorFile())
+
+	wal, err := NewWAL(walFile, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+	wal.SetLogger(log.TestingLogger())
+	if err := wal.Start(); err != nil {
+		t.Fatal(err)
+	}
+	defer wal.Stop()
+
+	chain, commits, err := makeBlockchainFromWAL(wal)
+	if err != nil {
+		t.Fatalf(err.Error())
+	}
+
+	stateDB, state, store := stateAndStore(config, privVal.GetPubKey())
+	store.chain = chain
+	store.commits = commits
+
+	// run the chain through state.ApplyBlock to build up the tendermint state
+	state = buildTMStateFromChain(config, stateDB, state, chain, mode)
+	latestAppHash := state.AppHash
+
+	// make a new client creator
+	dummyApp := dummy.NewPersistentDummyApplication(path.Join(config.DBDir(), "2"))
+	clientCreator2 := proxy.NewLocalClientCreator(dummyApp)
+	if nBlocks > 0 {
+		// run nBlocks against a new client to build up the app state.
+		// use a throwaway tendermint state
+		proxyApp := proxy.NewAppConns(clientCreator2, nil)
+		stateDB, state, _ := stateAndStore(config, privVal.GetPubKey())
+		buildAppStateFromChain(proxyApp, stateDB, state, chain, nBlocks, mode)
+	}
+
+	// now start the app using the handshake - it should sync
+	handshaker := NewHandshaker(stateDB, state, store)
+	proxyApp := proxy.NewAppConns(clientCreator2, handshaker)
+	if err := proxyApp.Start(); err != nil {
+		t.Fatalf("Error starting proxy app connections: %v", err)
+	}
+	defer proxyApp.Stop()
+
+	// get the latest app hash from the app
+	res, err := proxyApp.Query().InfoSync(abci.RequestInfo{""})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// the app hash should be synced up
+	if !bytes.Equal(latestAppHash, res.LastBlockAppHash) {
+		t.Fatalf("Expected app hashes to match after handshake/replay. got %X, expected %X", res.LastBlockAppHash, latestAppHash)
+	}
+
+	expectedBlocksToSync := NUM_BLOCKS - nBlocks
+	if nBlocks == NUM_BLOCKS && mode > 0 {
+		expectedBlocksToSync += 1
+	} else if nBlocks > 0 && mode == 1 {
+		expectedBlocksToSync += 1
+	}
+
+	if handshaker.NBlocks() != expectedBlocksToSync {
+		t.Fatalf("Expected handshake to sync %d blocks, got %d", expectedBlocksToSync, handshaker.NBlocks())
+	}
 }
 
-func TestReplayCrashBeforeWritePrecommit(t *testing.T) {
-	cs, newBlockCh, voteMsg, f := setupReplayTest(7, false) // precommit
-	cs.evsw.AddListenerForEvent("tester", types.EventStringPolka(), func(data events.EventData) {
-		// Set LastSig
-		var err error
-		var msg ConsensusLogMessage
-		wire.ReadJSON(&msg, []byte(voteMsg), &err)
-		vote := msg.Msg.(msgInfo).Msg.(*VoteMessage)
-		if err != nil {
-			t.Fatalf("Error reading json data: %v", err)
-		}
-		cs.privValidator.LastSignBytes = types.SignBytes(cs.state.ChainID, vote.Vote)
-		cs.privValidator.LastSignature = vote.Vote.Signature
-	})
-	runReplayTest(t, cs, f, newBlockCh)
+func applyBlock(stateDB dbm.DB, st sm.State, blk *types.Block, proxyApp proxy.AppConns) sm.State {
+	testPartSize := st.ConsensusParams.BlockPartSizeBytes
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+
+	blkID := types.BlockID{blk.Hash(), blk.MakePartSet(testPartSize).Header()}
+	newState, err := blockExec.ApplyBlock(st, blkID, blk)
+	if err != nil {
+		panic(err)
+	}
+	return newState
+}
+
+func buildAppStateFromChain(proxyApp proxy.AppConns, stateDB dbm.DB,
+	state sm.State, chain []*types.Block, nBlocks int, mode uint) {
+	// start a new app without handshake, play nBlocks blocks
+	if err := proxyApp.Start(); err != nil {
+		panic(err)
+	}
+	defer proxyApp.Stop()
+
+	validators := types.TM2PB.Validators(state.Validators)
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+		panic(err)
+	}
+
+	switch mode {
+	case 0:
+		for i := 0; i < nBlocks; i++ {
+			block := chain[i]
+			state = applyBlock(stateDB, state, block, proxyApp)
+		}
+	case 1, 2:
+		for i := 0; i < nBlocks-1; i++ {
+			block := chain[i]
+			state = applyBlock(stateDB, state, block, proxyApp)
+		}
+
+		if mode == 2 {
+			// update the dummy height and apphash
+			// as if we ran commit but not
+			state = applyBlock(stateDB, state, chain[nBlocks-1], proxyApp)
+		}
+	}
+
+}
+
+func buildTMStateFromChain(config *cfg.Config, stateDB dbm.DB, state sm.State, chain []*types.Block, mode uint) sm.State {
+	// run the whole chain against this client to build up the tendermint state
+	clientCreator := proxy.NewLocalClientCreator(dummy.NewPersistentDummyApplication(path.Join(config.DBDir(), "1")))
+	proxyApp := proxy.NewAppConns(clientCreator, nil) // sm.NewHandshaker(config, state, store, ReplayLastBlock))
+	if err := proxyApp.Start(); err != nil {
+		panic(err)
+	}
+	defer proxyApp.Stop()
+
+	validators := types.TM2PB.Validators(state.Validators)
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+		panic(err)
+	}
+
+	switch mode {
+	case 0:
+		// sync right up
+		for _, block := range chain {
+			state = applyBlock(stateDB, state, block, proxyApp)
+		}
+
+	case 1, 2:
+		// sync up to the penultimate as if we stored the block.
+		// whether we commit or not depends on the appHash
+		for _, block := range chain[:len(chain)-1] {
+			state = applyBlock(stateDB, state, block, proxyApp)
+		}
+
+		// apply the final block to a state copy so we can
+		// get the right next appHash but keep the state back
+		applyBlock(stateDB, state, chain[len(chain)-1], proxyApp)
+	}
+
+	return state
+}
+
+//--------------------------
+// utils for making blocks
+
+func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
+	// Search for height marker
+	gr, found, err := wal.SearchForEndHeight(0, &WALSearchOptions{})
+	if err != nil {
+		return nil, nil, err
+	}
+	if !found {
+		return nil, nil, errors.New(cmn.Fmt("WAL does not contain height %d.", 1))
+	}
+	defer gr.Close() // nolint: errcheck
+
+	// log.Notice("Build a blockchain by reading from the WAL")
+
+	var blocks []*types.Block
+	var commits []*types.Commit
+
+	var thisBlockParts *types.PartSet
+	var thisBlockCommit *types.Commit
+	var height int64
+
+	dec := NewWALDecoder(gr)
+	for {
+		msg, err := dec.Decode()
+		if err == io.EOF {
+			break
+		} else if err != nil {
+			return nil, nil, err
+		}
+
+		piece := readPieceFromWAL(msg)
+		if piece == nil {
+			continue
+		}
+
+		switch p := piece.(type) {
+		case EndHeightMessage:
+			// if its not the first one, we have a full block
+			if thisBlockParts != nil {
+				var n int
+				block := wire.ReadBinary(&types.Block{}, thisBlockParts.GetReader(), 0, &n, &err).(*types.Block)
+				if err != nil {
+					panic(err)
+				}
+				if block.Height != height+1 {
+					panic(cmn.Fmt("read bad block from wal. got height %d, expected %d", block.Height, height+1))
+				}
+				commitHeight := thisBlockCommit.Precommits[0].Height
+				if commitHeight != height+1 {
+					panic(cmn.Fmt("commit doesnt match. got height %d, expected %d", commitHeight, height+1))
+				}
+				blocks = append(blocks, block)
+				commits = append(commits, thisBlockCommit)
+				height += 1
+			}
+		case *types.PartSetHeader:
+			thisBlockParts = types.NewPartSetFromHeader(*p)
+		case *types.Part:
+			_, err := thisBlockParts.AddPart(p, false)
+			if err != nil {
+				return nil, nil, err
+			}
+		case *types.Vote:
+			if p.Type == types.VoteTypePrecommit {
+				thisBlockCommit = &types.Commit{
+					BlockID:    p.BlockID,
+					Precommits: []*types.Vote{p},
+				}
+			}
+		}
+	}
+	// grab the last block too
+	var n int
+	block := wire.ReadBinary(&types.Block{}, thisBlockParts.GetReader(), 0, &n, &err).(*types.Block)
+	if err != nil {
+		panic(err)
+	}
+	if block.Height != height+1 {
+		panic(cmn.Fmt("read bad block from wal. got height %d, expected %d", block.Height, height+1))
+	}
+	commitHeight := thisBlockCommit.Precommits[0].Height
+	if commitHeight != height+1 {
+		panic(cmn.Fmt("commit doesnt match. got height %d, expected %d", commitHeight, height+1))
+	}
+	blocks = append(blocks, block)
+	commits = append(commits, thisBlockCommit)
+	return blocks, commits, nil
+}
+
+func readPieceFromWAL(msg *TimedWALMessage) interface{} {
+	// for logging
+	switch m := msg.Msg.(type) {
+	case msgInfo:
+		switch msg := m.Msg.(type) {
+		case *ProposalMessage:
+			return &msg.Proposal.BlockPartsHeader
+		case *BlockPartMessage:
+			return msg.Part
+		case *VoteMessage:
+			return msg.Vote
+		}
+	case EndHeightMessage:
+		return m
+	}
+
+	return nil
+}
+
+// fresh state and mock store
+func stateAndStore(config *cfg.Config, pubKey crypto.PubKey) (dbm.DB, sm.State, *mockBlockStore) {
+	stateDB := dbm.NewMemDB()
+	state, _ := sm.MakeGenesisStateFromFile(config.GenesisFile())
+	store := NewMockBlockStore(config, state.ConsensusParams)
+	return stateDB, state, store
+}
+
+//----------------------------------
+// mock block store
+
+type mockBlockStore struct {
+	config  *cfg.Config
+	params  types.ConsensusParams
+	chain   []*types.Block
+	commits []*types.Commit
+}
+
+// TODO: NewBlockStore(db.NewMemDB) ...
+func NewMockBlockStore(config *cfg.Config, params types.ConsensusParams) *mockBlockStore {
+	return &mockBlockStore{config, params, nil, nil}
+}
+
+func (bs *mockBlockStore) Height() int64                       { return int64(len(bs.chain)) }
+func (bs *mockBlockStore) LoadBlock(height int64) *types.Block { return bs.chain[height-1] }
+func (bs *mockBlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
+	block := bs.chain[height-1]
+	return &types.BlockMeta{
+		BlockID: types.BlockID{block.Hash(), block.MakePartSet(bs.params.BlockPartSizeBytes).Header()},
+		Header:  block.Header,
+	}
+}
+func (bs *mockBlockStore) LoadBlockPart(height int64, index int) *types.Part { return nil }
+func (bs *mockBlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
+}
+func (bs *mockBlockStore) LoadBlockCommit(height int64) *types.Commit {
+	return bs.commits[height-1]
+}
+func (bs *mockBlockStore) LoadSeenCommit(height int64) *types.Commit {
+	return bs.commits[height-1]
 }

consensus/ticker.go

@@ -0,0 +1,134 @@
+package consensus
+
+import (
+	"time"
+
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
+)
+
+var (
+	tickTockBufferSize = 10
+)
+
+// TimeoutTicker is a timer that schedules timeouts
+// conditional on the height/round/step in the timeoutInfo.
+// The timeoutInfo.Duration may be non-positive.
+type TimeoutTicker interface {
+	Start() error
+	Stop() error
+	Chan() <-chan timeoutInfo       // on which to receive a timeout
+	ScheduleTimeout(ti timeoutInfo) // reset the timer
+
+	SetLogger(log.Logger)
+}
+
+// timeoutTicker wraps time.Timer,
+// scheduling timeouts only for greater height/round/step
+// than what it's already seen.
+// Timeouts are scheduled along the tickChan,
+// and fired on the tockChan.
+type timeoutTicker struct {
+	cmn.BaseService
+
+	timer    *time.Timer
+	tickChan chan timeoutInfo // for scheduling timeouts
+	tockChan chan timeoutInfo // for notifying about them
+}
+
+// NewTimeoutTicker returns a new TimeoutTicker.
+func NewTimeoutTicker() TimeoutTicker {
+	tt := &timeoutTicker{
+		timer:    time.NewTimer(0),
+		tickChan: make(chan timeoutInfo, tickTockBufferSize),
+		tockChan: make(chan timeoutInfo, tickTockBufferSize),
+	}
+	tt.BaseService = *cmn.NewBaseService(nil, "TimeoutTicker", tt)
+	tt.stopTimer() // don't want to fire until the first scheduled timeout
+	return tt
+}
+
+// OnStart implements cmn.Service. It starts the timeout routine.
+func (t *timeoutTicker) OnStart() error {
+
+	go t.timeoutRoutine()
+
+	return nil
+}
+
+// OnStop implements cmn.Service. It stops the timeout routine.
+func (t *timeoutTicker) OnStop() {
+	t.BaseService.OnStop()
+	t.stopTimer()
+}
+
+// Chan returns a channel on which timeouts are sent.
+func (t *timeoutTicker) Chan() <-chan timeoutInfo {
+	return t.tockChan
+}
+
+// ScheduleTimeout schedules a new timeout by sending on the internal tickChan.
+// The timeoutRoutine is always available to read from tickChan, so this won't block.
+// The scheduling may fail if the timeoutRoutine has already scheduled a timeout for a later height/round/step.
+func (t *timeoutTicker) ScheduleTimeout(ti timeoutInfo) {
+	t.tickChan <- ti
+}
+
+//-------------------------------------------------------------
+
+// stop the timer and drain if necessary
+func (t *timeoutTicker) stopTimer() {
+	// Stop() returns false if it was already fired or was stopped
+	if !t.timer.Stop() {
+		select {
+		case <-t.timer.C:
+		default:
+			t.Logger.Debug("Timer already stopped")
+		}
+	}
+}
+
+// send on tickChan to start a new timer.
+// timers are interupted and replaced by new ticks from later steps
+// timeouts of 0 on the tickChan will be immediately relayed to the tockChan
+func (t *timeoutTicker) timeoutRoutine() {
+	t.Logger.Debug("Starting timeout routine")
+	var ti timeoutInfo
+	for {
+		select {
+		case newti := <-t.tickChan:
+			t.Logger.Debug("Received tick", "old_ti", ti, "new_ti", newti)
+
+			// ignore tickers for old height/round/step
+			if newti.Height < ti.Height {
+				continue
+			} else if newti.Height == ti.Height {
+				if newti.Round < ti.Round {
+					continue
+				} else if newti.Round == ti.Round {
+					if ti.Step > 0 && newti.Step <= ti.Step {
+						continue
+					}
+				}
+			}
+
+			// stop the last timer
+			t.stopTimer()
+
+			// update timeoutInfo and reset timer
+			// NOTE time.Timer allows duration to be non-positive
+			ti = newti
+			t.timer.Reset(ti.Duration)
+			t.Logger.Debug("Scheduled timeout", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
+		case <-t.timer.C:
+			t.Logger.Info("Timed out", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
+			// go routine here guarantees timeoutRoutine doesn't block.
+			// Determinism comes from playback in the receiveRoutine.
+			// We can eliminate it by merging the timeoutRoutine into receiveRoutine
+			//  and managing the timeouts ourselves with a millisecond ticker
+			go func(toi timeoutInfo) { t.tockChan <- toi }(ti)
+		case <-t.Quit:
+			return
+		}
+	}
+}

consensus/types/height_vote_set.go

@@ -1,11 +1,11 @@
-package consensus
+package types
 
 import (
 	"strings"
 	"sync"
 
-	. "github.com/tendermint/go-common"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 type RoundVoteSet struct {
@@ -24,19 +24,21 @@ but which round is not known in advance, so when a peer
 provides a precommit for a round greater than mtx.round,
 we create a new entry in roundVoteSets but also remember the
 peer to prevent abuse.
+We let each peer provide us with up to 2 unexpected "catchup" rounds.
+One for their LastCommit round, and another for the official commit round.
 */
 type HeightVoteSet struct {
 	chainID string
-	height  int
+	height  int64
 	valSet  *types.ValidatorSet
 
 	mtx               sync.Mutex
 	round             int                  // max tracked round
 	roundVoteSets     map[int]RoundVoteSet // keys: [0...round]
-	peerCatchupRounds map[string]int       // keys: peer.Key; values: round
+	peerCatchupRounds map[string][]int     // keys: peer.Key; values: at most 2 rounds
 }
 
-func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *HeightVoteSet {
+func NewHeightVoteSet(chainID string, height int64, valSet *types.ValidatorSet) *HeightVoteSet {
 	hvs := &HeightVoteSet{
 		chainID: chainID,
 	}
@@ -44,20 +46,20 @@ func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *H
 	return hvs
 }
 
-func (hvs *HeightVoteSet) Reset(height int, valSet *types.ValidatorSet) {
+func (hvs *HeightVoteSet) Reset(height int64, valSet *types.ValidatorSet) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 
 	hvs.height = height
 	hvs.valSet = valSet
 	hvs.roundVoteSets = make(map[int]RoundVoteSet)
-	hvs.peerCatchupRounds = make(map[string]int)
+	hvs.peerCatchupRounds = make(map[string][]int)
 
 	hvs.addRound(0)
 	hvs.round = 0
 }
 
-func (hvs *HeightVoteSet) Height() int {
+func (hvs *HeightVoteSet) Height() int64 {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	return hvs.height
@@ -74,7 +76,7 @@ func (hvs *HeightVoteSet) SetRound(round int) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	if hvs.round != 0 && (round < hvs.round+1) {
-		PanicSanity("SetRound() must increment hvs.round")
+		cmn.PanicSanity("SetRound() must increment hvs.round")
 	}
 	for r := hvs.round + 1; r <= round; r++ {
 		if _, ok := hvs.roundVoteSets[r]; ok {
@@ -87,9 +89,9 @@ func (hvs *HeightVoteSet) SetRound(round int) {
 
 func (hvs *HeightVoteSet) addRound(round int) {
 	if _, ok := hvs.roundVoteSets[round]; ok {
-		PanicSanity("addRound() for an existing round")
+		cmn.PanicSanity("addRound() for an existing round")
 	}
-	log.Debug("addRound(round)", "round", round)
+	// log.Debug("addRound(round)", "round", round)
 	prevotes := types.NewVoteSet(hvs.chainID, hvs.height, round, types.VoteTypePrevote, hvs.valSet)
 	precommits := types.NewVoteSet(hvs.chainID, hvs.height, round, types.VoteTypePrecommit, hvs.valSet)
 	hvs.roundVoteSets[round] = RoundVoteSet{
@@ -100,24 +102,27 @@ func (hvs *HeightVoteSet) addRound(round int) {
 
 // Duplicate votes return added=false, err=nil.
 // By convention, peerKey is "" if origin is self.
-func (hvs *HeightVoteSet) AddByIndex(valIndex int, vote *types.Vote, peerKey string) (added bool, address []byte, err error) {
+func (hvs *HeightVoteSet) AddVote(vote *types.Vote, peerKey string) (added bool, err error) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
+	if !types.IsVoteTypeValid(vote.Type) {
+		return
+	}
 	voteSet := hvs.getVoteSet(vote.Round, vote.Type)
 	if voteSet == nil {
-		if _, ok := hvs.peerCatchupRounds[peerKey]; !ok {
+		if rndz := hvs.peerCatchupRounds[peerKey]; len(rndz) < 2 {
 			hvs.addRound(vote.Round)
 			voteSet = hvs.getVoteSet(vote.Round, vote.Type)
-			hvs.peerCatchupRounds[peerKey] = vote.Round
+			hvs.peerCatchupRounds[peerKey] = append(rndz, vote.Round)
 		} else {
 			// Peer has sent a vote that does not match our round,
 			// for more than one round.  Bad peer!
 			// TODO punish peer.
-			log.Warn("Deal with peer giving votes from unwanted rounds")
+			// log.Warn("Deal with peer giving votes from unwanted rounds")
 			return
 		}
 	}
-	added, address, err = voteSet.AddByIndex(valIndex, vote)
+	added, err = voteSet.AddVote(vote)
 	return
 }
 
@@ -133,17 +138,19 @@ func (hvs *HeightVoteSet) Precommits(round int) *types.VoteSet {
 	return hvs.getVoteSet(round, types.VoteTypePrecommit)
 }
 
-// Last round that has +2/3 prevotes for a particular block or nil.
+// Last round and blockID that has +2/3 prevotes for a particular block or nil.
 // Returns -1 if no such round exists.
-func (hvs *HeightVoteSet) POLRound() int {
+func (hvs *HeightVoteSet) POLInfo() (polRound int, polBlockID types.BlockID) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	for r := hvs.round; r >= 0; r-- {
-		if hvs.getVoteSet(r, types.VoteTypePrevote).HasTwoThirdsMajority() {
-			return r
+		rvs := hvs.getVoteSet(r, types.VoteTypePrevote)
+		polBlockID, ok := rvs.TwoThirdsMajority()
+		if ok {
+			return r, polBlockID
 		}
 	}
-	return -1
+	return -1, types.BlockID{}
 }
 
 func (hvs *HeightVoteSet) getVoteSet(round int, type_ byte) *types.VoteSet {
@@ -157,7 +164,7 @@ func (hvs *HeightVoteSet) getVoteSet(round int, type_ byte) *types.VoteSet {
 	case types.VoteTypePrecommit:
 		return rvs.Precommits
 	default:
-		PanicSanity(Fmt("Unexpected vote type %X", type_))
+		cmn.PanicSanity(cmn.Fmt("Unexpected vote type %X", type_))
 		return nil
 	}
 }
@@ -167,6 +174,8 @@ func (hvs *HeightVoteSet) String() string {
 }
 
 func (hvs *HeightVoteSet) StringIndented(indent string) string {
+	hvs.mtx.Lock()
+	defer hvs.mtx.Unlock()
 	vsStrings := make([]string, 0, (len(hvs.roundVoteSets)+1)*2)
 	// rounds 0 ~ hvs.round inclusive
 	for round := 0; round <= hvs.round; round++ {
@@ -185,10 +194,27 @@ func (hvs *HeightVoteSet) StringIndented(indent string) string {
 		voteSetString = roundVoteSet.Precommits.StringShort()
 		vsStrings = append(vsStrings, voteSetString)
 	}
-	return Fmt(`HeightVoteSet{H:%v R:0~%v
+	return cmn.Fmt(`HeightVoteSet{H:%v R:0~%v
 %s  %v
 %s}`,
 		hvs.height, hvs.round,
 		indent, strings.Join(vsStrings, "\n"+indent+"  "),
 		indent)
 }
+
+// If a peer claims that it has 2/3 majority for given blockKey, call this.
+// NOTE: if there are too many peers, or too much peer churn,
+// this can cause memory issues.
+// TODO: implement ability to remove peers too
+func (hvs *HeightVoteSet) SetPeerMaj23(round int, type_ byte, peerID string, blockID types.BlockID) {
+	hvs.mtx.Lock()
+	defer hvs.mtx.Unlock()
+	if !types.IsVoteTypeValid(type_) {
+		return
+	}
+	voteSet := hvs.getVoteSet(round, type_)
+	if voteSet == nil {
+		return
+	}
+	voteSet.SetPeerMaj23(peerID, blockID)
+}

consensus/types/height_vote_set_test.go

@@ -0,0 +1,69 @@
+package types
+
+import (
+	"testing"
+	"time"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+var config *cfg.Config // NOTE: must be reset for each _test.go file
+
+func init() {
+	config = cfg.ResetTestRoot("consensus_height_vote_set_test")
+}
+
+func TestPeerCatchupRounds(t *testing.T) {
+	valSet, privVals := types.RandValidatorSet(10, 1)
+
+	hvs := NewHeightVoteSet(config.ChainID, 1, valSet)
+
+	vote999_0 := makeVoteHR(t, 1, 999, privVals, 0)
+	added, err := hvs.AddVote(vote999_0, "peer1")
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from peer", added, err)
+	}
+
+	vote1000_0 := makeVoteHR(t, 1, 1000, privVals, 0)
+	added, err = hvs.AddVote(vote1000_0, "peer1")
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from peer", added, err)
+	}
+
+	vote1001_0 := makeVoteHR(t, 1, 1001, privVals, 0)
+	added, err = hvs.AddVote(vote1001_0, "peer1")
+	if err != nil {
+		t.Error("AddVote error", err)
+	}
+	if added {
+		t.Error("Expected to *not* add vote from peer, too many catchup rounds.")
+	}
+
+	added, err = hvs.AddVote(vote1001_0, "peer2")
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from another peer")
+	}
+
+}
+
+func makeVoteHR(t *testing.T, height int64, round int, privVals []*types.PrivValidatorFS, valIndex int) *types.Vote {
+	privVal := privVals[valIndex]
+	vote := &types.Vote{
+		ValidatorAddress: privVal.GetAddress(),
+		ValidatorIndex:   valIndex,
+		Height:           height,
+		Round:            round,
+		Timestamp:        time.Now().UTC(),
+		Type:             types.VoteTypePrecommit,
+		BlockID:          types.BlockID{[]byte("fakehash"), types.PartSetHeader{}},
+	}
+	chainID := config.ChainID
+	err := privVal.SignVote(chainID, vote)
+	if err != nil {
+		panic(cmn.Fmt("Error signing vote: %v", err))
+		return nil
+	}
+	return vote
+}

consensus/types/reactor.go

@@ -0,0 +1,57 @@
+package types
+
+import (
+	"fmt"
+	"time"
+
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+//-----------------------------------------------------------------------------
+
+// PeerRoundState contains the known state of a peer.
+// NOTE: Read-only when returned by PeerState.GetRoundState().
+type PeerRoundState struct {
+	Height                   int64               // Height peer is at
+	Round                    int                 // Round peer is at, -1 if unknown.
+	Step                     RoundStepType       // Step peer is at
+	StartTime                time.Time           // Estimated start of round 0 at this height
+	Proposal                 bool                // True if peer has proposal for this round
+	ProposalBlockPartsHeader types.PartSetHeader //
+	ProposalBlockParts       *cmn.BitArray       //
+	ProposalPOLRound         int                 // Proposal's POL round. -1 if none.
+	ProposalPOL              *cmn.BitArray       // nil until ProposalPOLMessage received.
+	Prevotes                 *cmn.BitArray       // All votes peer has for this round
+	Precommits               *cmn.BitArray       // All precommits peer has for this round
+	LastCommitRound          int                 // Round of commit for last height. -1 if none.
+	LastCommit               *cmn.BitArray       // All commit precommits of commit for last height.
+	CatchupCommitRound       int                 // Round that we have commit for. Not necessarily unique. -1 if none.
+	CatchupCommit            *cmn.BitArray       // All commit precommits peer has for this height & CatchupCommitRound
+}
+
+// String returns a string representation of the PeerRoundState
+func (prs PeerRoundState) String() string {
+	return prs.StringIndented("")
+}
+
+// StringIndented returns a string representation of the PeerRoundState
+func (prs PeerRoundState) StringIndented(indent string) string {
+	return fmt.Sprintf(`PeerRoundState{
+%s  %v/%v/%v @%v
+%s  Proposal %v -> %v
+%s  POL      %v (round %v)
+%s  Prevotes   %v
+%s  Precommits %v
+%s  LastCommit %v (round %v)
+%s  Catchup    %v (round %v)
+%s}`,
+		indent, prs.Height, prs.Round, prs.Step, prs.StartTime,
+		indent, prs.ProposalBlockPartsHeader, prs.ProposalBlockParts,
+		indent, prs.ProposalPOL, prs.ProposalPOLRound,
+		indent, prs.Prevotes,
+		indent, prs.Precommits,
+		indent, prs.LastCommit, prs.LastCommitRound,
+		indent, prs.CatchupCommit, prs.CatchupCommitRound,
+		indent)
+}

consensus/types/state.go

@@ -0,0 +1,131 @@
+package types
+
+import (
+	"fmt"
+	"time"
+
+	"github.com/tendermint/tendermint/types"
+)
+
+//-----------------------------------------------------------------------------
+// RoundStepType enum type
+
+// RoundStepType enumerates the state of the consensus state machine
+type RoundStepType uint8 // These must be numeric, ordered.
+
+const (
+	RoundStepNewHeight     = RoundStepType(0x01) // Wait til CommitTime + timeoutCommit
+	RoundStepNewRound      = RoundStepType(0x02) // Setup new round and go to RoundStepPropose
+	RoundStepPropose       = RoundStepType(0x03) // Did propose, gossip proposal
+	RoundStepPrevote       = RoundStepType(0x04) // Did prevote, gossip prevotes
+	RoundStepPrevoteWait   = RoundStepType(0x05) // Did receive any +2/3 prevotes, start timeout
+	RoundStepPrecommit     = RoundStepType(0x06) // Did precommit, gossip precommits
+	RoundStepPrecommitWait = RoundStepType(0x07) // Did receive any +2/3 precommits, start timeout
+	RoundStepCommit        = RoundStepType(0x08) // Entered commit state machine
+	// NOTE: RoundStepNewHeight acts as RoundStepCommitWait.
+)
+
+// String returns a string
+func (rs RoundStepType) String() string {
+	switch rs {
+	case RoundStepNewHeight:
+		return "RoundStepNewHeight"
+	case RoundStepNewRound:
+		return "RoundStepNewRound"
+	case RoundStepPropose:
+		return "RoundStepPropose"
+	case RoundStepPrevote:
+		return "RoundStepPrevote"
+	case RoundStepPrevoteWait:
+		return "RoundStepPrevoteWait"
+	case RoundStepPrecommit:
+		return "RoundStepPrecommit"
+	case RoundStepPrecommitWait:
+		return "RoundStepPrecommitWait"
+	case RoundStepCommit:
+		return "RoundStepCommit"
+	default:
+		return "RoundStepUnknown" // Cannot panic.
+	}
+}
+
+//-----------------------------------------------------------------------------
+
+// RoundState defines the internal consensus state.
+// It is Immutable when returned from ConsensusState.GetRoundState()
+// TODO: Actually, only the top pointer is copied,
+// so access to field pointers is still racey
+// NOTE: Not thread safe. Should only be manipulated by functions downstream
+// of the cs.receiveRoutine
+type RoundState struct {
+	Height             int64 // Height we are working on
+	Round              int
+	Step               RoundStepType
+	StartTime          time.Time
+	CommitTime         time.Time // Subjective time when +2/3 precommits for Block at Round were found
+	Validators         *types.ValidatorSet
+	Proposal           *types.Proposal
+	ProposalBlock      *types.Block
+	ProposalBlockParts *types.PartSet
+	LockedRound        int
+	LockedBlock        *types.Block
+	LockedBlockParts   *types.PartSet
+	Votes              *HeightVoteSet
+	CommitRound        int            //
+	LastCommit         *types.VoteSet // Last precommits at Height-1
+	LastValidators     *types.ValidatorSet
+}
+
+// RoundStateEvent returns the H/R/S of the RoundState as an event.
+func (rs *RoundState) RoundStateEvent() types.EventDataRoundState {
+	// XXX: copy the RoundState
+	// if we want to avoid this, we may need synchronous events after all
+	rs_ := *rs
+	edrs := types.EventDataRoundState{
+		Height:     rs.Height,
+		Round:      rs.Round,
+		Step:       rs.Step.String(),
+		RoundState: &rs_,
+	}
+	return edrs
+}
+
+// String returns a string
+func (rs *RoundState) String() string {
+	return rs.StringIndented("")
+}
+
+// StringIndented returns a string
+func (rs *RoundState) StringIndented(indent string) string {
+	return fmt.Sprintf(`RoundState{
+%s  H:%v R:%v S:%v
+%s  StartTime:     %v
+%s  CommitTime:    %v
+%s  Validators:    %v
+%s  Proposal:      %v
+%s  ProposalBlock: %v %v
+%s  LockedRound:   %v
+%s  LockedBlock:   %v %v
+%s  Votes:         %v
+%s  LastCommit:    %v
+%s  LastValidators:%v
+%s}`,
+		indent, rs.Height, rs.Round, rs.Step,
+		indent, rs.StartTime,
+		indent, rs.CommitTime,
+		indent, rs.Validators.StringIndented(indent+"    "),
+		indent, rs.Proposal,
+		indent, rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort(),
+		indent, rs.LockedRound,
+		indent, rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort(),
+		indent, rs.Votes.StringIndented(indent+"    "),
+		indent, rs.LastCommit.StringShort(),
+		indent, rs.LastValidators.StringIndented(indent+"    "),
+		indent)
+}
+
+// StringShort returns a string
+func (rs *RoundState) StringShort() string {
+	return fmt.Sprintf(`RoundState{H:%v R:%v S:%v ST:%v}`,
+		rs.Height, rs.Round, rs.Step, rs.StartTime)
+}

consensus/version.go

@@ -1,7 +1,7 @@
 package consensus
 
 import (
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 // kind of arbitrary
@@ -10,4 +10,4 @@ var Major = "0"    //
 var Minor = "2"    // replay refactor
 var Revision = "2" // validation -> commit
 
-var Version = Fmt("v%s/%s.%s.%s", Spec, Major, Minor, Revision)
+var Version = cmn.Fmt("v%s/%s.%s.%s", Spec, Major, Minor, Revision)

consensus/wal.go

@@ -1,145 +1,320 @@
 package consensus
 
 import (
-	"bufio"
-	"os"
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"hash/crc32"
+	"io"
+	"path/filepath"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-wire"
+	"github.com/pkg/errors"
+
+	wire "github.com/tendermint/go-wire"
 	"github.com/tendermint/tendermint/types"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+const (
+	// must be greater than params.BlockGossip.BlockPartSizeBytes + a few bytes
+	maxMsgSizeBytes = 1024 * 1024 // 1MB
 )
 
 //--------------------------------------------------------
 // types and functions for savings consensus messages
 
-type ConsensusLogMessage struct {
-	Time time.Time                    `json:"time"`
-	Msg  ConsensusLogMessageInterface `json:"msg"`
+type TimedWALMessage struct {
+	Time time.Time  `json:"time"` // for debugging purposes
+	Msg  WALMessage `json:"msg"`
 }
 
-type ConsensusLogMessageInterface interface{}
+// EndHeightMessage marks the end of the given height inside WAL.
+// @internal used by scripts/wal2json util.
+type EndHeightMessage struct {
+	Height int64 `json:"height"`
+}
+
+type WALMessage interface{}
 
 var _ = wire.RegisterInterface(
-	struct{ ConsensusLogMessageInterface }{},
+	struct{ WALMessage }{},
 	wire.ConcreteType{types.EventDataRoundState{}, 0x01},
 	wire.ConcreteType{msgInfo{}, 0x02},
 	wire.ConcreteType{timeoutInfo{}, 0x03},
+	wire.ConcreteType{EndHeightMessage{}, 0x04},
 )
 
 //--------------------------------------------------------
 // Simple write-ahead logger
 
+// WAL is an interface for any write-ahead logger.
+type WAL interface {
+	Save(WALMessage)
+	Group() *auto.Group
+	SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
+
+	Start() error
+	Stop() error
+	Wait()
+}
+
 // Write ahead logger writes msgs to disk before they are processed.
 // Can be used for crash-recovery and deterministic replay
 // TODO: currently the wal is overwritten during replay catchup
 //   give it a mode so it's either reading or appending - must read to end to start appending again
-type WAL struct {
-	fp     *os.File
-	exists bool // if the file already existed (restarted process)
-
-	done chan struct{}
+type baseWAL struct {
+	cmn.BaseService
 
+	group *auto.Group
 	light bool // ignore block parts
+
+	enc *WALEncoder
 }
 
-func NewWAL(file string, light bool) (*WAL, error) {
-	var walExists bool
-	if _, err := os.Stat(file); err == nil {
-		walExists = true
+func NewWAL(walFile string, light bool) (*baseWAL, error) {
+	err := cmn.EnsureDir(filepath.Dir(walFile), 0700)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to ensure WAL directory is in place")
 	}
-	fp, err := os.OpenFile(file, os.O_RDWR|os.O_APPEND|os.O_CREATE, 0600)
+
+	group, err := auto.OpenGroup(walFile)
 	if err != nil {
 		return nil, err
 	}
-	return &WAL{
-		fp:     fp,
-		exists: walExists,
-		done:   make(chan struct{}),
-		light:  light,
-	}, nil
+	wal := &baseWAL{
+		group: group,
+		light: light,
+		enc:   NewWALEncoder(group),
+	}
+	wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
+	return wal, nil
 }
 
-func (wal *WAL) Exists() bool {
-	if wal == nil {
-		log.Warn("consensus msg log is nil")
-		return false
+func (wal *baseWAL) Group() *auto.Group {
+	return wal.group
+}
+
+func (wal *baseWAL) OnStart() error {
+	size, err := wal.group.Head.Size()
+	if err != nil {
+		return err
+	} else if size == 0 {
+		wal.Save(EndHeightMessage{0})
 	}
-	return wal.exists
+	err = wal.group.Start()
+	return err
+}
+
+func (wal *baseWAL) OnStop() {
+	wal.BaseService.OnStop()
+	wal.group.Stop()
 }
 
 // called in newStep and for each pass in receiveRoutine
-func (wal *WAL) Save(clm ConsensusLogMessageInterface) {
-	if wal != nil {
-		if wal.light {
-			// in light mode we only write new steps, timeouts, and our own votes (no proposals, block parts)
-			if mi, ok := clm.(msgInfo); ok {
-				_ = mi
-				if mi.PeerKey != "" {
-					return
-				}
-			}
-		}
-		var n int
-		var err error
-		wire.WriteJSON(ConsensusLogMessage{time.Now(), clm}, wal.fp, &n, &err)
-		wire.WriteTo([]byte("\n"), wal.fp, &n, &err) // one message per line
-		if err != nil {
-			PanicQ(Fmt("Error writing msg to consensus wal. Error: %v \n\nMessage: %v", err, clm))
-		}
-	}
-}
-
-// Must not be called concurrently with a write.
-func (wal *WAL) Close() {
-	if wal != nil {
-		wal.fp.Close()
-	}
-	wal.done <- struct{}{}
-}
-
-func (wal *WAL) Wait() {
-	<-wal.done
-}
-
-func (wal *WAL) SeekFromEnd(found func([]byte) bool) (nLines int, err error) {
-	var current int64
-	// start at the end
-	current, err = wal.fp.Seek(0, 2)
-	if err != nil {
+func (wal *baseWAL) Save(msg WALMessage) {
+	if wal == nil {
 		return
 	}
 
-	// backup until we find the the right line
-	// current is how far we are from the beginning
-	for {
-		current -= 1
-		if current < 0 {
-			wal.fp.Seek(0, 0) // back to beginning
-			return
-		}
-		// backup one and read a new byte
-		if _, err = wal.fp.Seek(current, 0); err != nil {
-			return
-		}
-		b := make([]byte, 1)
-		if _, err = wal.fp.Read(b); err != nil {
-			return
-		}
-		if b[0] == '\n' || len(b) == 0 {
-			nLines += 1
-			// read a full line
-			reader := bufio.NewReader(wal.fp)
-			lineBytes, _ := reader.ReadBytes('\n')
-			if len(lineBytes) == 0 {
-				continue
-			}
-
-			if found(lineBytes) {
-				wal.fp.Seek(0, 1) // (?)
-				wal.fp.Seek(current, 0)
+	if wal.light {
+		// in light mode we only write new steps, timeouts, and our own votes (no proposals, block parts)
+		if mi, ok := msg.(msgInfo); ok {
+			if mi.PeerKey != "" {
 				return
 			}
 		}
 	}
+
+	// Write the wal message
+	if err := wal.enc.Encode(&TimedWALMessage{time.Now(), msg}); err != nil {
+		cmn.PanicQ(cmn.Fmt("Error writing msg to consensus wal: %v \n\nMessage: %v", err, msg))
+	}
+
+	// TODO: only flush when necessary
+	if err := wal.group.Flush(); err != nil {
+		cmn.PanicQ(cmn.Fmt("Error flushing consensus wal buf to file. Error: %v \n", err))
+	}
 }
+
+// WALSearchOptions are optional arguments to SearchForEndHeight.
+type WALSearchOptions struct {
+	// IgnoreDataCorruptionErrors set to true will result in skipping data corruption errors.
+	IgnoreDataCorruptionErrors bool
+}
+
+// SearchForEndHeight searches for the EndHeightMessage with the height and
+// returns an auto.GroupReader, whenever it was found or not and an error.
+// Group reader will be nil if found equals false.
+//
+// CONTRACT: caller must close group reader.
+func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	var msg *TimedWALMessage
+
+	// NOTE: starting from the last file in the group because we're usually
+	// searching for the last height. See replay.go
+	min, max := wal.group.MinIndex(), wal.group.MaxIndex()
+	wal.Logger.Debug("Searching for height", "height", height, "min", min, "max", max)
+	for index := max; index >= min; index-- {
+		gr, err = wal.group.NewReader(index)
+		if err != nil {
+			return nil, false, err
+		}
+
+		dec := NewWALDecoder(gr)
+		for {
+			msg, err = dec.Decode()
+			if err == io.EOF {
+				// check next file
+				break
+			}
+			if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
+				// do nothing
+			} else if err != nil {
+				gr.Close()
+				return nil, false, err
+			}
+
+			if m, ok := msg.Msg.(EndHeightMessage); ok {
+				if m.Height == height { // found
+					wal.Logger.Debug("Found", "height", height, "index", index)
+					return gr, true, nil
+				}
+			}
+		}
+		gr.Close()
+	}
+
+	return nil, false, nil
+}
+
+///////////////////////////////////////////////////////////////////////////////
+
+// A WALEncoder writes custom-encoded WAL messages to an output stream.
+//
+// Format: 4 bytes CRC sum + 4 bytes length + arbitrary-length value (go-wire encoded)
+type WALEncoder struct {
+	wr io.Writer
+}
+
+// NewWALEncoder returns a new encoder that writes to wr.
+func NewWALEncoder(wr io.Writer) *WALEncoder {
+	return &WALEncoder{wr}
+}
+
+// Encode writes the custom encoding of v to the stream.
+func (enc *WALEncoder) Encode(v *TimedWALMessage) error {
+	data := wire.BinaryBytes(v)
+
+	crc := crc32.Checksum(data, crc32c)
+	length := uint32(len(data))
+	totalLength := 8 + int(length)
+
+	msg := make([]byte, totalLength)
+	binary.BigEndian.PutUint32(msg[0:4], crc)
+	binary.BigEndian.PutUint32(msg[4:8], length)
+	copy(msg[8:], data)
+
+	_, err := enc.wr.Write(msg)
+
+	return err
+}
+
+///////////////////////////////////////////////////////////////////////////////
+
+// IsDataCorruptionError returns true if data has been corrupted inside WAL.
+func IsDataCorruptionError(err error) bool {
+	_, ok := err.(DataCorruptionError)
+	return ok
+}
+
+// DataCorruptionError is an error that occures if data on disk was corrupted.
+type DataCorruptionError struct {
+	cause error
+}
+
+func (e DataCorruptionError) Error() string {
+	return fmt.Sprintf("DataCorruptionError[%v]", e.cause)
+}
+
+func (e DataCorruptionError) Cause() error {
+	return e.cause
+}
+
+// A WALDecoder reads and decodes custom-encoded WAL messages from an input
+// stream. See WALEncoder for the format used.
+//
+// It will also compare the checksums and make sure data size is equal to the
+// length from the header. If that is not the case, error will be returned.
+type WALDecoder struct {
+	rd io.Reader
+}
+
+// NewWALDecoder returns a new decoder that reads from rd.
+func NewWALDecoder(rd io.Reader) *WALDecoder {
+	return &WALDecoder{rd}
+}
+
+// Decode reads the next custom-encoded value from its reader and returns it.
+func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
+	b := make([]byte, 4)
+
+	_, err := dec.rd.Read(b)
+	if err == io.EOF {
+		return nil, err
+	}
+	if err != nil {
+		return nil, fmt.Errorf("failed to read checksum: %v", err)
+	}
+	crc := binary.BigEndian.Uint32(b)
+
+	b = make([]byte, 4)
+	_, err = dec.rd.Read(b)
+	if err == io.EOF {
+		return nil, err
+	}
+	if err != nil {
+		return nil, fmt.Errorf("failed to read length: %v", err)
+	}
+	length := binary.BigEndian.Uint32(b)
+
+	if length > maxMsgSizeBytes {
+		return nil, DataCorruptionError{fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)}
+	}
+
+	data := make([]byte, length)
+	_, err = dec.rd.Read(data)
+	if err == io.EOF {
+		return nil, err
+	}
+	if err != nil {
+		return nil, fmt.Errorf("failed to read data: %v", err)
+	}
+
+	// check checksum before decoding data
+	actualCRC := crc32.Checksum(data, crc32c)
+	if actualCRC != crc {
+		return nil, DataCorruptionError{fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)}
+	}
+
+	var nn int
+	var res *TimedWALMessage // nolint: gosimple
+	res = wire.ReadBinary(&TimedWALMessage{}, bytes.NewBuffer(data), int(length), &nn, &err).(*TimedWALMessage)
+	if err != nil {
+		return nil, DataCorruptionError{fmt.Errorf("failed to decode data: %v", err)}
+	}
+
+	return res, err
+}
+
+type nilWAL struct{}
+
+func (nilWAL) Save(m WALMessage)  {}
+func (nilWAL) Group() *auto.Group { return nil }
+func (nilWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return nil, false, nil
+}
+func (nilWAL) Start() error { return nil }
+func (nilWAL) Stop() error  { return nil }
+func (nilWAL) Wait()        {}

consensus/wal_fuzz.go

@@ -0,0 +1,31 @@
+// +build gofuzz
+
+package consensus
+
+import (
+	"bytes"
+	"io"
+)
+
+func Fuzz(data []byte) int {
+	dec := NewWALDecoder(bytes.NewReader(data))
+	for {
+		msg, err := dec.Decode()
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			if msg != nil {
+				panic("msg != nil on error")
+			}
+			return 0
+		}
+		var w bytes.Buffer
+		enc := NewWALEncoder(&w)
+		err = enc.Encode(msg)
+		if err != nil {
+			panic(err)
+		}
+	}
+	return 1
+}

consensus/wal_generator.go

@@ -0,0 +1,201 @@
+package consensus
+
+import (
+	"bufio"
+	"bytes"
+	"fmt"
+	"math/rand"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/pkg/errors"
+	"github.com/tendermint/abci/example/dummy"
+	bc "github.com/tendermint/tendermint/blockchain"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+// WALWithNBlocks generates a consensus WAL. It does this by spining up a
+// stripped down version of node (proxy app, event bus, consensus state) with a
+// persistent dummy application and special consensus wal instance
+// (byteBufferWAL) and waits until numBlocks are created. Then it returns a WAL
+// content.
+func WALWithNBlocks(numBlocks int) (data []byte, err error) {
+	config := getConfig()
+
+	app := dummy.NewPersistentDummyApplication(filepath.Join(config.DBDir(), "wal_generator"))
+
+	logger := log.TestingLogger().With("wal_generator", "wal_generator")
+	logger.Info("generating WAL (last height msg excluded)", "numBlocks", numBlocks)
+
+	/////////////////////////////////////////////////////////////////////////////
+	// COPY PASTE FROM node.go WITH A FEW MODIFICATIONS
+	// NOTE: we can't import node package because of circular dependency
+	privValidatorFile := config.PrivValidatorFile()
+	privValidator := types.LoadOrGenPrivValidatorFS(privValidatorFile)
+	genDoc, err := types.GenesisDocFromFile(config.GenesisFile())
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to read genesis file")
+	}
+	stateDB := db.NewMemDB()
+	blockStoreDB := db.NewMemDB()
+	state, err := sm.MakeGenesisState(genDoc)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to make genesis state")
+	}
+	blockStore := bc.NewBlockStore(blockStoreDB)
+	handshaker := NewHandshaker(stateDB, state, blockStore)
+	proxyApp := proxy.NewAppConns(proxy.NewLocalClientCreator(app), handshaker)
+	proxyApp.SetLogger(logger.With("module", "proxy"))
+	if err := proxyApp.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start proxy app connections")
+	}
+	defer proxyApp.Stop()
+	eventBus := types.NewEventBus()
+	eventBus.SetLogger(logger.With("module", "events"))
+	if err := eventBus.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start event bus")
+	}
+	defer eventBus.Stop()
+	mempool := types.MockMempool{}
+	evpool := types.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+	consensusState := NewConsensusState(config.Consensus, state.Copy(), blockExec, blockStore, mempool, evpool)
+	consensusState.SetLogger(logger)
+	consensusState.SetEventBus(eventBus)
+	if privValidator != nil {
+		consensusState.SetPrivValidator(privValidator)
+	}
+	// END OF COPY PASTE
+	/////////////////////////////////////////////////////////////////////////////
+
+	// set consensus wal to buffered WAL, which will write all incoming msgs to buffer
+	var b bytes.Buffer
+	wr := bufio.NewWriter(&b)
+	numBlocksWritten := make(chan struct{})
+	wal := newByteBufferWAL(logger, NewWALEncoder(wr), int64(numBlocks), numBlocksWritten)
+	// see wal.go#103
+	wal.Save(EndHeightMessage{0})
+	consensusState.wal = wal
+
+	if err := consensusState.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start consensus state")
+	}
+	defer consensusState.Stop()
+
+	select {
+	case <-numBlocksWritten:
+		wr.Flush()
+		return b.Bytes(), nil
+	case <-time.After(1 * time.Minute):
+		wr.Flush()
+		return b.Bytes(), fmt.Errorf("waited too long for tendermint to produce %d blocks (grep logs for `wal_generator`)", numBlocks)
+	}
+}
+
+// f**ing long, but unique for each test
+func makePathname() string {
+	// get path
+	p, err := os.Getwd()
+	if err != nil {
+		panic(err)
+	}
+	// fmt.Println(p)
+	sep := string(filepath.Separator)
+	return strings.Replace(p, sep, "_", -1)
+}
+
+func randPort() int {
+	// returns between base and base + spread
+	base, spread := 20000, 20000
+	return base + rand.Intn(spread)
+}
+
+func makeAddrs() (string, string, string) {
+	start := randPort()
+	return fmt.Sprintf("tcp://0.0.0.0:%d", start),
+		fmt.Sprintf("tcp://0.0.0.0:%d", start+1),
+		fmt.Sprintf("tcp://0.0.0.0:%d", start+2)
+}
+
+// getConfig returns a config for test cases
+func getConfig() *cfg.Config {
+	pathname := makePathname()
+	c := cfg.ResetTestRoot(fmt.Sprintf("%s_%d", pathname, cmn.RandInt()))
+
+	// and we use random ports to run in parallel
+	tm, rpc, grpc := makeAddrs()
+	c.P2P.ListenAddress = tm
+	c.RPC.ListenAddress = rpc
+	c.RPC.GRPCListenAddress = grpc
+	return c
+}
+
+// byteBufferWAL is a WAL which writes all msgs to a byte buffer. Writing stops
+// when the heightToStop is reached. Client will be notified via
+// signalWhenStopsTo channel.
+type byteBufferWAL struct {
+	enc               *WALEncoder
+	stopped           bool
+	heightToStop      int64
+	signalWhenStopsTo chan<- struct{}
+
+	logger log.Logger
+}
+
+// needed for determinism
+var fixedTime, _ = time.Parse(time.RFC3339, "2017-01-02T15:04:05Z")
+
+func newByteBufferWAL(logger log.Logger, enc *WALEncoder, nBlocks int64, signalStop chan<- struct{}) *byteBufferWAL {
+	return &byteBufferWAL{
+		enc:               enc,
+		heightToStop:      nBlocks,
+		signalWhenStopsTo: signalStop,
+		logger:            logger,
+	}
+}
+
+// Save writes message to the internal buffer except when heightToStop is
+// reached, in which case it will signal the caller via signalWhenStopsTo and
+// skip writing.
+func (w *byteBufferWAL) Save(m WALMessage) {
+	if w.stopped {
+		w.logger.Debug("WAL already stopped. Not writing message", "msg", m)
+		return
+	}
+
+	if endMsg, ok := m.(EndHeightMessage); ok {
+		w.logger.Debug("WAL write end height message", "height", endMsg.Height, "stopHeight", w.heightToStop)
+		if endMsg.Height == w.heightToStop {
+			w.logger.Debug("Stopping WAL at height", "height", endMsg.Height)
+			w.signalWhenStopsTo <- struct{}{}
+			w.stopped = true
+			return
+		}
+	}
+
+	w.logger.Debug("WAL Write Message", "msg", m)
+	err := w.enc.Encode(&TimedWALMessage{fixedTime, m})
+	if err != nil {
+		panic(fmt.Sprintf("failed to encode the msg %v", m))
+	}
+}
+
+func (w *byteBufferWAL) Group() *auto.Group {
+	panic("not implemented")
+}
+func (w *byteBufferWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return nil, false, nil
+}
+
+func (w *byteBufferWAL) Start() error { return nil }
+func (w *byteBufferWAL) Stop() error  { return nil }
+func (w *byteBufferWAL) Wait()        {}

consensus/wal_test.go

@@ -1,78 +1,132 @@
 package consensus
 
 import (
-	"io/ioutil"
-	"os"
-	"path"
-	"strings"
+	"bytes"
+	"crypto/rand"
+	"sync"
 	"testing"
+	"time"
 
-	. "github.com/tendermint/go-common"
+	wire "github.com/tendermint/go-wire"
+	"github.com/tendermint/tendermint/consensus/types"
+	tmtypes "github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 )
 
-var testTxt = `{"time":"2016-01-16T04:42:00.390Z","msg":[1,{"height":28219,"round":0,"step":"RoundStepPrevote"}]}
-{"time":"2016-01-16T04:42:00.390Z","msg":[2,{"msg":[20,{"ValidatorIndex":0,"Vote":{"height":28219,"round":0,"type":1,"block_hash":"67F9689F15BEC30BF311FB4C0C80C5E661AA44E0","block_parts_header":{"total":1,"hash":"DFFD4409A1E273ED61AC27CAF975F446020D5676"},"signature":"4CC6845A128E723A299B470CCBB2A158612AA51321447F6492F3DA57D135C27FCF4124B3B19446A248252BDA45B152819C76AAA5FD35E1C07091885CE6955E05"}}],"peer_key":""}]}
-{"time":"2016-01-16T04:42:00.392Z","msg":[1,{"height":28219,"round":0,"step":"RoundStepPrecommit"}]}
-{"time":"2016-01-16T04:42:00.392Z","msg":[2,{"msg":[20,{"ValidatorIndex":0,"Vote":{"height":28219,"round":0,"type":2,"block_hash":"67F9689F15BEC30BF311FB4C0C80C5E661AA44E0","block_parts_header":{"total":1,"hash":"DFFD4409A1E273ED61AC27CAF975F446020D5676"},"signature":"1B9924E010F47E0817695DFE462C531196E5A12632434DE12180BBA3EFDAD6B3960FDB9357AFF085EB61729A7D4A6AD8408555D7569C87D9028F280192FD4E05"}}],"peer_key":""}]}
-{"time":"2016-01-16T04:42:00.393Z","msg":[1,{"height":28219,"round":0,"step":"RoundStepCommit"}]}
-{"time":"2016-01-16T04:42:00.395Z","msg":[1,{"height":28220,"round":0,"step":"RoundStepNewHeight"}]}`
-
-func TestSeek(t *testing.T) {
-	f, err := ioutil.TempFile(os.TempDir(), "seek_test_")
-	if err != nil {
-		panic(err)
+func TestWALEncoderDecoder(t *testing.T) {
+	now := time.Now()
+	msgs := []TimedWALMessage{
+		TimedWALMessage{Time: now, Msg: EndHeightMessage{0}},
+		TimedWALMessage{Time: now, Msg: timeoutInfo{Duration: time.Second, Height: 1, Round: 1, Step: types.RoundStepPropose}},
 	}
 
-	stat, _ := f.Stat()
-	name := stat.Name()
+	b := new(bytes.Buffer)
 
-	_, err = f.WriteString(testTxt)
-	if err != nil {
-		panic(err)
-	}
-	f.Close()
+	for _, msg := range msgs {
+		b.Reset()
 
-	wal, err := NewWAL(path.Join(os.TempDir(), name), config.GetBool("cswal_light"))
-	if err != nil {
-		panic(err)
-	}
+		enc := NewWALEncoder(b)
+		err := enc.Encode(&msg)
+		require.NoError(t, err)
 
-	keyWord := "Precommit"
-	n, err := wal.SeekFromEnd(func(b []byte) bool {
-		if strings.Contains(string(b), keyWord) {
-			return true
-		}
-		return false
-	})
-	if err != nil {
-		panic(err)
-	}
+		dec := NewWALDecoder(b)
+		decoded, err := dec.Decode()
+		require.NoError(t, err)
 
-	// confirm n
-	spl := strings.Split(testTxt, "\n")
-	var i int
-	var s string
-	for i, s = range spl {
-		if strings.Contains(s, keyWord) {
-			break
-		}
+		assert.Equal(t, msg.Time.Truncate(time.Millisecond), decoded.Time)
+		assert.Equal(t, msg.Msg, decoded.Msg)
 	}
-	// n is lines from the end.
-	spl = spl[i:]
-	if n != len(spl) {
-		panic(Fmt("Wrong nLines. Got %d, expected %d", n, len(spl)))
-	}
-
-	b, err := ioutil.ReadAll(wal.fp)
-	if err != nil {
-		panic(err)
-	}
-	// first char is a \n
-	spl2 := strings.Split(strings.Trim(string(b), "\n"), "\n")
-	for i, s := range spl {
-		if s != spl2[i] {
-			panic(Fmt("Mismatch. Got %s, expected %s", spl2[i], s))
-		}
-	}
-
+}
+
+func TestSearchForEndHeight(t *testing.T) {
+	walBody, err := WALWithNBlocks(6)
+	if err != nil {
+		t.Fatal(err)
+	}
+	walFile := tempWALWithData(walBody)
+
+	wal, err := NewWAL(walFile, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	h := int64(3)
+	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
+	assert.NoError(t, err, cmn.Fmt("expected not to err on height %d", h))
+	assert.True(t, found, cmn.Fmt("expected to find end height for %d", h))
+	assert.NotNil(t, gr, "expected group not to be nil")
+	defer gr.Close()
+
+	dec := NewWALDecoder(gr)
+	msg, err := dec.Decode()
+	assert.NoError(t, err, "expected to decode a message")
+	rs, ok := msg.Msg.(tmtypes.EventDataRoundState)
+	assert.True(t, ok, "expected message of type EventDataRoundState")
+	assert.Equal(t, rs.Height, h+1, cmn.Fmt("wrong height"))
+}
+
+var initOnce sync.Once
+
+func registerInterfacesOnce() {
+	initOnce.Do(func() {
+		var _ = wire.RegisterInterface(
+			struct{ WALMessage }{},
+			wire.ConcreteType{[]byte{}, 0x10},
+		)
+	})
+}
+
+func nBytes(n int) []byte {
+	buf := make([]byte, n)
+	n, _ = rand.Read(buf)
+	return buf[:n]
+}
+
+func benchmarkWalDecode(b *testing.B, n int) {
+	registerInterfacesOnce()
+
+	buf := new(bytes.Buffer)
+	enc := NewWALEncoder(buf)
+
+	data := nBytes(n)
+	enc.Encode(&TimedWALMessage{Msg: data, Time: time.Now().Round(time.Second)})
+
+	encoded := buf.Bytes()
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		buf.Write(encoded)
+		dec := NewWALDecoder(buf)
+		if _, err := dec.Decode(); err != nil {
+			b.Fatal(err)
+		}
+	}
+	b.ReportAllocs()
+}
+
+func BenchmarkWalDecode512B(b *testing.B) {
+	benchmarkWalDecode(b, 512)
+}
+
+func BenchmarkWalDecode10KB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024)
+}
+func BenchmarkWalDecode100KB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024)
+}
+func BenchmarkWalDecode1MB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024)
+}
+func BenchmarkWalDecode10MB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024*1024)
+}
+func BenchmarkWalDecode100MB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024*1024)
+}
+func BenchmarkWalDecode1GB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024*1024)
 }

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = python -msphinx
+SPHINXPROJ    = Tendermint
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/README.md

@@ -0,0 +1,14 @@
+Here lies our documentation. After making edits, run:
+
+```
+pip install -r requirements.txt
+make html
+```
+
+to build the docs locally then open the file `_build/html/index.html` in your browser.
+
+**WARNING:** This documentation is intended to be viewed at:
+
+https://tendermint.readthedocs.io
+
+and may contain broken internal links when viewed from Github.

docs/_static/custom_collapsible_code.css

@@ -0,0 +1,17 @@
+.toggle {
+    padding-bottom: 1em ;
+}
+
+.toggle .header {
+    display: block;
+    clear: both;
+    cursor: pointer;
+}
+
+.toggle .header:after {
+    content: " ▼";
+}
+
+.toggle .header.open:after {
+    content: " ▲";
+}

docs/_static/custom_collapsible_code.js

@@ -0,0 +1,10 @@
+let makeCodeBlocksCollapsible = function() {
+    $(".toggle > *").hide();
+    $(".toggle .header").show();
+    $(".toggle .header").click(function() {
+        $(this).parent().children().not(".header").toggle({"duration": 400});
+        $(this).parent().children(".header").toggleClass("open");
+    });
+};
+// we could use the }(); way if we would have access to jQuery in HEAD, i.e. we would need to force the theme
+// to load jQuery before our custom scripts

docs/_templates/layout.html

@@ -0,0 +1,20 @@
+{% extends "!layout.html" %}
+
+{% set css_files = css_files + ["_static/custom_collapsible_code.css"] %}
+
+# sadly, I didn't find a css style way to add custom JS to a list that is automagically added to head like CSS (above) #}
+{% block extrahead %}
+<script type="text/javascript" src="_static/custom_collapsible_code.js"></script>
+{% endblock %}
+
+{% block footer %}
+<script type="text/javascript">
+    $(document).ready(function() {
+        // using this approach as we don't have access to the jQuery selectors
+        // when executing the function on load in HEAD
+        makeCodeBlocksCollapsible();
+    });
+</script>
+{% endblock %}
+
+

docs/abci-cli.rst

@@ -0,0 +1,292 @@
+Using ABCI-CLI
+==============
+
+To facilitate testing and debugging of ABCI servers and simple apps, we
+built a CLI, the ``abci-cli``, for sending ABCI messages from the
+command line.
+
+Install
+-------
+
+Make sure you `have Go installed <https://golang.org/doc/install>`__.
+
+Next, install the ``abci-cli`` tool and example applications:
+
+::
+
+    go get -u github.com/tendermint/abci/cmd/abci-cli
+
+If this fails, you may need to use ``glide`` to get vendored
+dependencies:
+
+::
+
+    go get github.com/Masterminds/glide
+    cd $GOPATH/src/github.com/tendermint/abci
+    glide install
+    go install ./cmd/abci-cli
+
+Now run ``abci-cli`` to see the list of commands:
+
+::
+
+    Usage:
+      abci-cli [command]
+
+    Available Commands:
+      batch       Run a batch of abci commands against an application
+      check_tx    Validate a tx
+      commit      Commit the application state and return the Merkle root hash
+      console     Start an interactive abci console for multiple commands
+      counter     ABCI demo example
+      deliver_tx  Deliver a new tx to the application
+      dummy       ABCI demo example
+      echo        Have the application echo a message
+      help        Help about any command
+      info        Get some info about the application
+      query       Query the application state
+      set_option  Set an options on the application
+
+    Flags:
+          --abci string      socket or grpc (default "socket")
+          --address string   address of application socket (default "tcp://127.0.0.1:46658")
+      -h, --help             help for abci-cli
+      -v, --verbose          print the command and results as if it were a console session
+
+                                          Use "abci-cli [command] --help" for more information about a command.
+
+
+Dummy - First Example
+---------------------
+
+The ``abci-cli`` tool lets us send ABCI messages to our application, to
+help build and debug them.
+
+The most important messages are ``deliver_tx``, ``check_tx``, and
+``commit``, but there are others for convenience, configuration, and
+information purposes.
+
+Let's start a dummy application, which was installed at the same time as
+``abci-cli`` above. The dummy just stores transactions in a merkle tree:
+
+::
+
+    abci-cli dummy
+
+In another terminal, run
+
+::
+
+    abci-cli echo hello
+    abci-cli info
+
+You'll see something like:
+
+::
+
+    -> data: hello
+    -> data.hex: 68656C6C6F
+
+and:
+
+::
+
+    -> data: {"size":0}
+    -> data.hex: 7B2273697A65223A307D
+
+An ABCI application must provide two things:
+
+-  a socket server
+-  a handler for ABCI messages
+
+When we run the ``abci-cli`` tool we open a new connection to the
+application's socket server, send the given ABCI message, and wait for a
+response.
+
+The server may be generic for a particular language, and we provide a
+`reference implementation in
+Golang <https://github.com/tendermint/abci/tree/master/server>`__. See
+the `list of other ABCI
+implementations <./ecosystem.html>`__ for servers in
+other languages.
+
+The handler is specific to the application, and may be arbitrary, so
+long as it is deterministic and conforms to the ABCI interface
+specification.
+
+So when we run ``abci-cli info``, we open a new connection to the ABCI
+server, which calls the ``Info()`` method on the application, which
+tells us the number of transactions in our Merkle tree.
+
+Now, since every command opens a new connection, we provide the
+``abci-cli console`` and ``abci-cli batch`` commands, to allow multiple
+ABCI messages to be sent over a single connection.
+
+Running ``abci-cli console`` should drop you in an interactive console
+for speaking ABCI messages to your application.
+
+Try running these commands:
+
+::
+
+    > echo hello
+    -> code: OK
+    -> data: hello
+    -> data.hex: 0x68656C6C6F
+    
+    > info
+    -> code: OK
+    -> data: {"size":0}
+    -> data.hex: 0x7B2273697A65223A307D
+    
+    > commit
+    -> code: OK
+    
+    > deliver_tx "abc"
+    -> code: OK
+    
+    > info
+    -> code: OK
+    -> data: {"size":1}
+    -> data.hex: 0x7B2273697A65223A317D
+    
+    > commit
+    -> code: OK
+    -> data.hex: 0x49DFD15CCDACDEAE9728CB01FBB5E8688CA58B91
+    
+    > query "abc"
+    -> code: OK
+    -> log: exists
+    -> height: 0
+    -> value: abc
+    -> value.hex: 616263
+    
+    > deliver_tx "def=xyz"
+    -> code: OK
+    
+    > commit
+    -> code: OK
+    -> data.hex: 0x70102DB32280373FBF3F9F89DA2A20CE2CD62B0B
+    
+    > query "def"
+    -> code: OK
+    -> log: exists
+    -> height: 0
+    -> value: xyz
+    -> value.hex: 78797A
+
+Note that if we do ``deliver_tx "abc"`` it will store ``(abc, abc)``,
+but if we do ``deliver_tx "abc=efg"`` it will store ``(abc, efg)``.
+
+Similarly, you could put the commands in a file and run
+``abci-cli --verbose batch < myfile``.
+
+Counter - Another Example
+-------------------------
+
+Now that we've got the hang of it, let's try another application, the
+"counter" app.
+
+The counter app doesn't use a Merkle tree, it just counts how many times
+we've sent a transaction, asked for a hash, or committed the state. The
+result of ``commit`` is just the number of transactions sent.
+
+This application has two modes: ``serial=off`` and ``serial=on``.
+
+When ``serial=on``, transactions must be a big-endian encoded
+incrementing integer, starting at 0.
+
+If ``serial=off``, there are no restrictions on transactions.
+
+We can toggle the value of ``serial`` using the ``set_option`` ABCI
+message.
+
+When ``serial=on``, some transactions are invalid. In a live blockchain,
+transactions collect in memory before they are committed into blocks. To
+avoid wasting resources on invalid transactions, ABCI provides the
+``check_tx`` message, which application developers can use to accept or
+reject transactions, before they are stored in memory or gossipped to
+other peers.
+
+In this instance of the counter app, ``check_tx`` only allows
+transactions whose integer is greater than the last committed one.
+
+Let's kill the console and the dummy application, and start the counter
+app:
+
+::
+
+    abci-cli counter
+
+In another window, start the ``abci-cli console``:
+
+::
+
+    > set_option serial on
+    -> code: OK
+    
+    > check_tx 0x00
+    -> code: OK
+    
+    > check_tx 0xff
+    -> code: OK
+    
+    > deliver_tx 0x00
+    -> code: OK
+    
+    > check_tx 0x00
+    -> code: BadNonce
+    -> log: Invalid nonce. Expected >= 1, got 0
+    
+    > deliver_tx 0x01
+    -> code: OK
+    
+    > deliver_tx 0x04
+    -> code: BadNonce
+    -> log: Invalid nonce. Expected 2, got 4
+    
+    > info
+    -> code: OK
+    -> data: {"hashes":0,"txs":2}
+    -> data.hex: 0x7B22686173686573223A302C22747873223A327D
+
+This is a very simple application, but between ``counter`` and
+``dummy``, its easy to see how you can build out arbitrary application
+states on top of the ABCI. `Hyperledger's
+Burrow <https://github.com/hyperledger/burrow>`__ also runs atop ABCI,
+bringing with it Ethereum-like accounts, the Ethereum virtual-machine,
+Monax's permissioning scheme, and native contracts extensions.
+
+But the ultimate flexibility comes from being able to write the
+application easily in any language.
+
+We have implemented the counter in a number of languages (see the
+example directory).
+
+To run the Node JS version, ``cd`` to ``example/js`` and run
+
+::
+
+    node app.js
+
+(you'll have to kill the other counter application process). In another
+window, run the console and those previous ABCI commands. You should get
+the same results as for the Go version.
+
+Bounties
+--------
+
+Want to write the counter app in your favorite language?! We'd be happy
+to add you to our `ecosystem <https://tendermint.com/ecosystem>`__!
+We're also offering `bounties <https://tendermint.com/bounties>`__ for
+implementations in new languages!
+
+The ``abci-cli`` is designed strictly for testing and debugging. In a
+real deployment, the role of sending messages is taken by Tendermint,
+which connects to the app using three separate connections, each with
+its own pattern of messages.
+
+For more information, see the `application developers
+guide <./app-development.html>`__. For examples of running an ABCI
+app with Tendermint, see the `getting started
+guide <./getting-started.html>`__.

docs/app-architecture.rst

@@ -0,0 +1,125 @@
+Application Architecture Guide
+==============================
+
+Overview
+--------
+
+A blockchain application is more than the consensus engine and the
+transaction logic (eg. smart contracts, business logic) as implemented
+in the ABCI app. There are also (mobile, web, desktop) clients that will
+need to connect and make use of the app. We will assume for now that you
+have a well designed transactions and database model, but maybe this
+will be the topic of another article. This article is more interested in
+various ways of setting up the "plumbing" and connecting these pieces,
+and demonstrating some evolving best practices.
+
+Security
+--------
+
+A very important aspect when constructing a blockchain is security. The
+consensus model can be DoSed (no consensus possible) by corrupting 1/3
+of the validators and exploited (writing arbitrary blocks) by corrupting
+2/3 of the validators. So, while the security is not that of the
+"weakest link", you should take care that the "average link" is
+sufficiently hardened.
+
+One big attack surface on the validators is the communication between
+the ABCI app and the tendermint core. This should be highly protected.
+Ideally, the app and the core are running on the same machine, so no
+external agent can target the communication channel. You can use unix
+sockets (with permissions preventing access from other users), or even
+compile the two apps into one binary if the ABCI app is also writen in
+go. If you are unable to do that due to language support, then the ABCI
+app should bind a TCP connection to localhost (127.0.0.1), which is less
+efficient and secure, but still not reachable from outside. If you must
+run the ABCI app and tendermint core on separate machines, make sure you
+have a secure communication channel (ssh tunnel?)
+
+Now assuming, you have linked together your app and the core securely,
+you must also make sure no one can get on the machine it is hosted on.
+At this point it is basic network security. Run on a secure operating
+system (SELinux?). Limit who has access to the machine (user accounts,
+but also where the physical machine is hosted). Turn off all services
+except for ssh, which should only be accessible by some well-guarded
+public/private key pairs (no password). And maybe even firewall off
+access to the ports used by the validators, so only known validators can
+connect.
+
+There was also a suggestion on slack from @jhon about compiling
+everything together with a unikernel for more security, such as
+`Mirage <https://mirage.io>`__ or
+`UNIK <https://github.com/emc-advanced-dev/unik>`__.
+
+Connecting your client to the blockchain
+----------------------------------------
+
+Tendermint Core RPC
+~~~~~~~~~~~~~~~~~~~
+
+The concept is that the ABCI app is completely hidden from the outside
+world and only communicated through a tested and secured `interface
+exposed by the tendermint core <./specification/rpc.html>`__. This interface
+exposes a lot of data on the block header and consensus process, which
+is quite useful for externally verifying the system. It also includes
+3(!) methods to broadcast a transaction (propose it for the blockchain,
+and possibly await a response). And one method to query app-specific
+data from the ABCI application.
+
+Pros:
+* Server code already written
+* Access to block headers to validate merkle proofs (nice for light clients)
+* Basic read/write functionality is supported
+
+Cons:
+* Limited interface to app. All queries must be serialized into
+[]byte (less expressive than JSON over HTTP) and there is no way to push
+data from ABCI app to the client (eg. notify me if account X receives a
+transaction)
+
+Custom ABCI server
+~~~~~~~~~~~~~~~~~~
+
+This was proposed by @wolfposd on slack and demonstrated by
+`TMChat <https://github.com/wolfposd/TMChat>`__, a sample app. The
+concept is to write a custom server for your app (with typical REST
+API/websockets/etc for easy use by a mobile app). This custom server is
+in the same binary as the ABCI app and data store, so can easily react
+to complex events there that involve understanding the data format (send
+a message if my balance drops below 500). All "writes" sent to this
+server are proxied via websocket/JSON-RPC to tendermint core. When they
+come back as deliver\_tx over ABCI, they will be written to the data
+store. For "reads", we can do any queries we wish that are supported by
+our architecture, using any web technology that is useful. The general
+architecture is shown in the following diagram:
+
+Pros: \* Separates application logic from blockchain logic \* Allows
+much richer, more flexible client-facing API \* Allows pub-sub, watching
+certain fields, etc.
+
+Cons: \* Access to ABCI app can be dangerous (be VERY careful not to
+write unless it comes from the validator node) \* No direct access to
+the blockchain headers to verify tx \* You must write your own API (but
+maybe that's a pro...)
+
+Hybrid solutions
+~~~~~~~~~~~~~~~~
+
+Likely the least secure but most versatile. The client can access both
+the tendermint node for all blockchain info, as well as a custom app
+server, for complex queries and pub-sub on the abci app.
+
+Pros: All from both above solutions
+
+Cons: Even more complexity; even more attack vectors (less
+security)
+
+Scalability
+-----------
+
+Read replica using non-validating nodes? They could forward transactions
+to the validators (fewer connections, more security), and locally allow
+all queries in any of the above configurations. Thus, while
+transaction-processing speed is limited by the speed of the abci app and
+the number of validators, one should be able to scale our read
+performance to quite an extent (until the replication process drains too
+many resources from the validator nodes).

docs/app-development.rst

@@ -0,0 +1,631 @@
+Application Development Guide
+=============================
+
+ABCI Design
+-----------
+
+The purpose of ABCI is to provide a clean interface between state
+transition machines on one computer and the mechanics of their
+replication across multiple computers. The former we call 'application
+logic' and the latter the 'consensus engine'. Application logic
+validates transactions and optionally executes transactions against some
+persistent state. A consensus engine ensures all transactions are
+replicated in the same order on every machine. We call each machine in a
+consensus engine a 'validator', and each validator runs the same
+transactions through the same application logic. In particular, we are
+interested in blockchain-style consensus engines, where transactions are
+committed in hash-linked blocks.
+
+The ABCI design has a few distinct components:
+
+-  message protocol
+
+   -  pairs of request and response messages
+   -  consensus makes requests, application responds
+   -  defined using protobuf
+
+-  server/client
+
+   -  consensus engine runs the client
+   -  application runs the server
+   -  two implementations:
+
+      -  async raw bytes
+      -  grpc
+
+-  blockchain protocol
+
+   -  abci is connection oriented
+   -  Tendermint Core maintains three connections:
+
+      -  `mempool connection <#mempool-connection>`__: for checking if
+         transactions should be relayed before they are committed; only
+         uses ``CheckTx``
+      -  `consensus connection <#consensus-connection>`__: for executing
+         transactions that have been committed. Message sequence is -
+         for every block -
+         ``BeginBlock, [DeliverTx, ...], EndBlock, Commit``
+      -  `query connection <#query-connection>`__: for querying the
+         application state; only uses Query and Info
+
+The mempool and consensus logic act as clients, and each maintains an
+open ABCI connection with the application, which hosts an ABCI server.
+Shown are the request and response types sent on each connection.
+
+Message Protocol
+----------------
+
+The message protocol consists of pairs of requests and responses. Some
+messages have no fields, while others may include byte-arrays, strings,
+or integers. See the ``message Request`` and ``message Response``
+definitions in `the protobuf definition
+file <https://github.com/tendermint/abci/blob/master/types/types.proto>`__,
+and the `protobuf
+documentation <https://developers.google.com/protocol-buffers/docs/overview>`__
+for more details.
+
+For each request, a server should respond with the corresponding
+response, where order of requests is preserved in the order of
+responses.
+
+Server
+------
+
+To use ABCI in your programming language of choice, there must be a ABCI
+server in that language. Tendermint supports two kinds of implementation
+of the server:
+
+-  Asynchronous, raw socket server (Tendermint Socket Protocol, also
+   known as TSP or Teaspoon)
+-  GRPC
+
+Both can be tested using the ``abci-cli`` by setting the ``--abci`` flag
+appropriately (ie. to ``socket`` or ``grpc``).
+
+See examples, in various stages of maintenance, in
+`Go <https://github.com/tendermint/abci/tree/master/server>`__,
+`JavaScript <https://github.com/tendermint/js-abci>`__,
+`Python <https://github.com/tendermint/abci/tree/master/example/python3/abci>`__,
+`C++ <https://github.com/mdyring/cpp-tmsp>`__, and
+`Java <https://github.com/jTendermint/jabci>`__.
+
+GRPC
+~~~~
+
+If GRPC is available in your language, this is the easiest approach,
+though it will have significant performance overhead.
+
+To get started with GRPC, copy in the `protobuf
+file <https://github.com/tendermint/abci/blob/master/types/types.proto>`__
+and compile it using the GRPC plugin for your language. For instance,
+for golang, the command is
+``protoc --go_out=plugins=grpc:. types.proto``. See the `grpc
+documentation for more details <http://www.grpc.io/docs/>`__. ``protoc``
+will autogenerate all the necessary code for ABCI client and server in
+your language, including whatever interface your application must
+satisfy to be used by the ABCI server for handling requests.
+
+TSP
+~~~
+
+If GRPC is not available in your language, or you require higher
+performance, or otherwise enjoy programming, you may implement your own
+ABCI server using the Tendermint Socket Protocol, known affectionately
+as Teaspoon. The first step is still to auto-generate the relevant data
+types and codec in your language using ``protoc``. Messages coming over
+the socket are Protobuf3 encoded, but additionally length-prefixed to
+facilitate use as a streaming protocol. Protobuf3 doesn't have an
+official length-prefix standard, so we use our own. The first byte in
+the prefix represents the length of the Big Endian encoded length. The
+remaining bytes in the prefix are the Big Endian encoded length.
+
+For example, if the Protobuf3 encoded ABCI message is 0xDEADBEEF (4
+bytes), the length-prefixed message is 0x0104DEADBEEF. If the Protobuf3
+encoded ABCI message is 65535 bytes long, the length-prefixed message
+would be like 0x02FFFF....
+
+Note this prefixing does not apply for grpc.
+
+An ABCI server must also be able to support multiple connections, as
+Tendermint uses three connections.
+
+Client
+------
+
+There are currently two use-cases for an ABCI client. One is a testing
+tool, as in the ``abci-cli``, which allows ABCI requests to be sent via
+command line. The other is a consensus engine, such as Tendermint Core,
+which makes requests to the application every time a new transaction is
+received or a block is committed.
+
+It is unlikely that you will need to implement a client. For details of
+our client, see
+`here <https://github.com/tendermint/abci/tree/master/client>`__.
+
+Most of the examples below are from `dummy application
+<https://github.com/tendermint/abci/blob/master/example/dummy/dummy.go>`__,
+which is a part of the abci repo. `persistent_dummy application
+<https://github.com/tendermint/abci/blob/master/example/dummy/persistent_dummy.go>`__
+is used to show ``BeginBlock``, ``EndBlock`` and ``InitChain``
+example implementations.
+
+Blockchain Protocol
+-------------------
+
+In ABCI, a transaction is simply an arbitrary length byte-array. It is
+the application's responsibility to define the transaction codec as they
+please, and to use it for both CheckTx and DeliverTx.
+
+Note that there are two distinct means for running transactions,
+corresponding to stages of 'awareness' of the transaction in the
+network. The first stage is when a transaction is received by a
+validator from a client into the so-called mempool or transaction pool -
+this is where we use CheckTx. The second is when the transaction is
+successfully committed on more than 2/3 of validators - where we use
+DeliverTx. In the former case, it may not be necessary to run all the
+state transitions associated with the transaction, as the transaction
+may not ultimately be committed until some much later time, when the
+result of its execution will be different. For instance, an Ethereum
+ABCI app would check signatures and amounts in CheckTx, but would not
+actually execute any contract code until the DeliverTx, so as to avoid
+executing state transitions that have not been finalized.
+
+To formalize the distinction further, two explicit ABCI connections are
+made between Tendermint Core and the application: the mempool connection
+and the consensus connection. We also make a third connection, the query
+connection, to query the local state of the app.
+
+Mempool Connection
+~~~~~~~~~~~~~~~~~~
+
+The mempool connection is used *only* for CheckTx requests. Transactions
+are run using CheckTx in the same order they were received by the
+validator. If the CheckTx returns ``OK``, the transaction is kept in
+memory and relayed to other peers in the same order it was received.
+Otherwise, it is discarded.
+
+CheckTx requests run concurrently with block processing; so they should
+run against a copy of the main application state which is reset after
+every block. This copy is necessary to track transitions made by a
+sequence of CheckTx requests before they are included in a block. When a
+block is committed, the application must ensure to reset the mempool
+state to the latest committed state. Tendermint Core will then filter
+through all transactions in the mempool, removing any that were included
+in the block, and re-run the rest using CheckTx against the post-Commit
+mempool state.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *DummyApplication) CheckTx(tx []byte) types.Result {
+          return types.OK
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        ResponseCheckTx requestCheckTx(RequestCheckTx req) {
+            byte[] transaction = req.getTx().toByteArray();
+
+            // validate transaction
+
+            if (notValid) {
+                return ResponseCheckTx.newBuilder().setCode(CodeType.BadNonce).setLog("invalid tx").build();
+            } else {
+                return ResponseCheckTx.newBuilder().setCode(CodeType.OK).build();
+            }
+        }
+
+Consensus Connection
+~~~~~~~~~~~~~~~~~~~~
+
+The consensus connection is used only when a new block is committed, and
+communicates all information from the block in a series of requests:
+``BeginBlock, [DeliverTx, ...], EndBlock, Commit``. That is, when a
+block is committed in the consensus, we send a list of DeliverTx
+requests (one for each transaction) sandwiched by BeginBlock and
+EndBlock requests, and followed by a Commit.
+
+DeliverTx
+^^^^^^^^^
+
+DeliverTx is the workhorse of the blockchain. Tendermint sends the
+DeliverTx requests asynchronously but in order, and relies on the
+underlying socket protocol (ie. TCP) to ensure they are received by the
+app in order. They have already been ordered in the global consensus by
+the Tendermint protocol.
+
+DeliverTx returns a abci.Result, which includes a Code, Data, and Log.
+The code may be non-zero (non-OK), meaning the corresponding transaction
+should have been rejected by the mempool, but may have been included in
+a block by a Byzantine proposer.
+
+The block header will be updated (TODO) to include some commitment to
+the results of DeliverTx, be it a bitarray of non-OK transactions, or a
+merkle root of the data returned by the DeliverTx requests, or both.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        // tx is either "key=value" or just arbitrary bytes
+        func (app *DummyApplication) DeliverTx(tx []byte) types.Result {
+          parts := strings.Split(string(tx), "=")
+          if len(parts) == 2 {
+            app.state.Set([]byte(parts[0]), []byte(parts[1]))
+          } else {
+            app.state.Set(tx, tx)
+          }
+          return types.OK
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        /**
+         * Using Protobuf types from the protoc compiler, we always start with a byte[]
+         */
+        ResponseDeliverTx deliverTx(RequestDeliverTx request) {
+            byte[] transaction  = request.getTx().toByteArray();
+
+            // validate your transaction
+
+            if (notValid) {
+                return ResponseDeliverTx.newBuilder().setCode(CodeType.BadNonce).setLog("transaction was invalid").build();
+            } else {
+                ResponseDeliverTx.newBuilder().setCode(CodeType.OK).build();
+            }
+
+        }
+
+Commit
+^^^^^^
+
+Once all processing of the block is complete, Tendermint sends the
+Commit request and blocks waiting for a response. While the mempool may
+run concurrently with block processing (the BeginBlock, DeliverTxs, and
+EndBlock), it is locked for the Commit request so that its state can be
+safely reset during Commit. This means the app *MUST NOT* do any
+blocking communication with the mempool (ie. broadcast\_tx) during
+Commit, or there will be deadlock. Note also that all remaining
+transactions in the mempool are replayed on the mempool connection
+(CheckTx) following a commit.
+
+The app should respond to the Commit request with a byte array, which is the deterministic
+state root of the application. It is included in the header of the next
+block. It can be used to provide easily verified Merkle-proofs of the
+state of the application.
+
+It is expected that the app will persist state to disk on Commit. The
+option to have all transactions replayed from some previous block is the
+job of the `Handshake <#handshake>`__.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *DummyApplication) Commit() types.Result {
+          hash := app.state.Hash()
+          return types.NewResultOK(hash, "")
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        ResponseCommit requestCommit(RequestCommit requestCommit) {
+
+            // update the internal app-state
+            byte[] newAppState = calculateAppState();
+
+            // and return it to the node
+            return ResponseCommit.newBuilder().setCode(CodeType.OK).setData(ByteString.copyFrom(newAppState)).build();
+        }
+
+BeginBlock
+^^^^^^^^^^
+
+The BeginBlock request can be used to run some code at the beginning of
+every block. It also allows Tendermint to send the current block hash
+and header to the application, before it sends any of the transactions.
+
+The app should remember the latest height and header (ie. from which it
+has run a successful Commit) so that it can tell Tendermint where to
+pick up from when it restarts. See information on the Handshake, below.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        // Track the block hash and header information
+        func (app *PersistentDummyApplication) BeginBlock(params types.RequestBeginBlock) {
+          // update latest block info
+          app.blockHeader = params.Header
+
+          // reset valset changes
+          app.changes = make([]*types.Validator, 0)
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        /*
+         * all types come from protobuf definition
+         */
+        ResponseBeginBlock requestBeginBlock(RequestBeginBlock req) {
+
+            Header header = req.getHeader();
+            byte[] prevAppHash = header.getAppHash().toByteArray();
+            long prevHeight = header.getHeight();
+            long numTxs = header.getNumTxs();
+
+            // run your pre-block logic. Maybe prepare a state snapshot, message components, etc
+
+            return ResponseBeginBlock.newBuilder().build();
+        }
+
+EndBlock
+^^^^^^^^
+
+The EndBlock request can be used to run some code at the end of every block.
+Additionally, the response may contain a list of validators, which can be used
+to update the validator set. To add a new validator or update an existing one,
+simply include them in the list returned in the EndBlock response. To remove
+one, include it in the list with a ``power`` equal to ``0``. Tendermint core
+will take care of updating the validator set. Note the change in voting power
+must be strictly less than 1/3 per block. Otherwise it will be impossible for a
+light client to prove the transition externally. See the `light client docs
+<https://godoc.org/github.com/tendermint/tendermint/lite#hdr-How_We_Track_Validators>`__
+for details on how it tracks validators. Tendermint core will fail with an
+error if the change in voting power is more or equal than 1/3.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        // Update the validator set
+        func (app *PersistentDummyApplication) EndBlock(req types.RequestEndBlock) types.ResponseEndBlock {
+          return types.ResponseEndBlock{ValidatorUpdates: app.ValUpdates}
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        /*
+         * Assume that one validator changes. The new validator has a power of 10
+         */
+        ResponseEndBlock requestEndBlock(RequestEndBlock req) {
+            final long currentHeight = req.getHeight();
+            final byte[] validatorPubKey = getValPubKey();
+
+            ResponseEndBlock.Builder builder = ResponseEndBlock.newBuilder();
+            builder.addDiffs(1, Types.Validator.newBuilder().setPower(10L).setPubKey(ByteString.copyFrom(validatorPubKey)).build());
+
+            return builder.build();
+        }
+
+Query Connection
+~~~~~~~~~~~~~~~~
+
+This connection is used to query the application without engaging
+consensus. It's exposed over the tendermint core rpc, so clients can
+query the app without exposing a server on the app itself, but they must
+serialize each query as a single byte array. Additionally, certain
+"standardized" queries may be used to inform local decisions, for
+instance about which peers to connect to.
+
+Tendermint Core currently uses the Query connection to filter peers upon
+connecting, according to IP address or public key. For instance,
+returning non-OK ABCI response to either of the following queries will
+cause Tendermint to not connect to the corresponding peer:
+
+-  ``p2p/filter/addr/<addr>``, where ``<addr>`` is an IP address.
+-  ``p2p/filter/pubkey/<pubkey>``, where ``<pubkey>`` is the hex-encoded
+   ED25519 key of the node (not it's validator key)
+
+Note: these query formats are subject to change!
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *DummyApplication) Query(reqQuery types.RequestQuery) (resQuery types.ResponseQuery) {
+          if reqQuery.Prove {
+            value, proof, exists := app.state.Proof(reqQuery.Data)
+            resQuery.Index = -1 // TODO make Proof return index
+            resQuery.Key = reqQuery.Data
+            resQuery.Value = value
+            resQuery.Proof = proof
+            if exists {
+              resQuery.Log = "exists"
+            } else {
+              resQuery.Log = "does not exist"
+            }
+            return
+          } else {
+            index, value, exists := app.state.Get(reqQuery.Data)
+            resQuery.Index = int64(index)
+            resQuery.Value = value
+            if exists {
+              resQuery.Log = "exists"
+            } else {
+              resQuery.Log = "does not exist"
+            }
+            return
+          }
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        ResponseQuery requestQuery(RequestQuery req) {
+            final boolean isProveQuery = req.getProve();
+            final ResponseQuery.Builder responseBuilder = ResponseQuery.newBuilder();
+
+            if (isProveQuery) {
+                com.app.example.ProofResult proofResult = generateProof(req.getData().toByteArray());
+                final byte[] proofAsByteArray = proofResult.getAsByteArray();
+
+                responseBuilder.setProof(ByteString.copyFrom(proofAsByteArray));
+                responseBuilder.setKey(req.getData());
+                responseBuilder.setValue(ByteString.copyFrom(proofResult.getData()));
+                responseBuilder.setLog(result.getLogValue());
+            } else {
+                byte[] queryData = req.getData().toByteArray();
+
+                final com.app.example.QueryResult result = generateQueryResult(queryData);
+
+                responseBuilder.setIndex(result.getIndex());
+                responseBuilder.setValue(ByteString.copyFrom(result.getValue()));
+                responseBuilder.setLog(result.getLogValue());
+            }
+
+            return responseBuilder.build();
+        }
+
+Handshake
+~~~~~~~~~
+
+When the app or tendermint restarts, they need to sync to a common
+height. When an ABCI connection is first established, Tendermint will
+call ``Info`` on the Query connection. The response should contain the
+LastBlockHeight and LastBlockAppHash - the former is the last block for
+which the app ran Commit successfully, the latter is the response
+from that Commit.
+
+Using this information, Tendermint will determine what needs to be
+replayed, if anything, against the app, to ensure both Tendermint and
+the app are synced to the latest block height.
+
+If the app returns a LastBlockHeight of 0, Tendermint will just replay
+all blocks.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *DummyApplication) Info(req types.RequestInfo) (resInfo types.ResponseInfo) {
+          return types.ResponseInfo{Data: cmn.Fmt("{\"size\":%v}", app.state.Size())}
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        ResponseInfo requestInfo(RequestInfo req) {
+            final byte[] lastAppHash = getLastAppHash();
+            final long lastHeight = getLastHeight();
+            return ResponseInfo.newBuilder().setLastBlockAppHash(ByteString.copyFrom(lastAppHash)).setLastBlockHeight(lastHeight).build();
+        }
+
+Genesis
+~~~~~~~
+
+``InitChain`` will be called once upon the genesis. ``params`` includes the
+initial validator set. Later on, it may be extended to take parts of the
+consensus params.
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        // Save the validators in the merkle tree
+        func (app *PersistentDummyApplication) InitChain(params types.RequestInitChain) {
+          for _, v := range params.Validators {
+            r := app.updateValidator(v)
+            if r.IsErr() {
+              app.logger.Error("Error updating validators", "r", r)
+            }
+          }
+        }
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Java Example**
+
+    .. code-block:: java
+
+        /*
+         * all types come from protobuf definition
+         */
+        ResponseInitChain requestInitChain(RequestInitChain req) {
+            final int validatorsCount = req.getValidatorsCount();
+            final List<Types.Validator> validatorsList = req.getValidatorsList();
+
+            validatorsList.forEach((validator) -> {
+                long power = validator.getPower();
+                byte[] validatorPubKey = validator.getPubKey().toByteArray();
+
+                // do somehing for validator setup in app
+            });
+
+            return ResponseInitChain.newBuilder().build();
+        }

docs/architecture/README.md

@@ -0,0 +1,5 @@
+# Architecture Decision Records
+
+This is a location to record all high-level architecture decisions in the tendermint project.  Not the implementation details, but the reasoning that happened.  This should be refered to for guidance of the "right way" to extend the application.  And if we notice that the original decisions were lacking, we should have another open discussion, record the new decisions here, and then modify the code to match.
+
+Read up on the concept in this [blog post](https://product.reverb.com/documenting-architecture-decisions-the-reverb-way-a3563bb24bd0#.78xhdix6t).

docs/architecture/adr-001-logging.md

@@ -0,0 +1,216 @@
+# ADR 1: Logging
+
+## Context
+
+Current logging system in Tendermint is very static and not flexible enough.
+
+Issues: [358](https://github.com/tendermint/tendermint/issues/358), [375](https://github.com/tendermint/tendermint/issues/375).
+
+What we want from the new system:
+
+- per package dynamic log levels
+- dynamic logger setting (logger tied to the processing struct)
+- conventions
+- be more visually appealing
+
+"dynamic" here means the ability to set smth in runtime.
+
+## Decision
+
+### 1) An interface
+
+First, we will need an interface for all of our libraries (`tmlibs`, Tendermint, etc.). My personal preference is go-kit `Logger` interface (see Appendix A.), but that is too much a bigger change. Plus we will still need levels.
+
+```go
+# log.go
+type Logger interface {
+    Debug(msg string, keyvals ...interface{}) error
+    Info(msg string, keyvals ...interface{}) error
+    Error(msg string, keyvals ...interface{}) error
+
+	  With(keyvals ...interface{}) Logger
+}
+```
+
+On a side note: difference between `Info` and `Notice` is subtle. We probably
+could do without `Notice`. Don't think we need `Panic` or `Fatal` as a part of
+the interface. These funcs could be implemented as helpers. In fact, we already
+have some in `tmlibs/common`.
+
+- `Debug` - extended output for devs
+- `Info` - all that is useful for a user
+- `Error` - errors
+
+`Notice` should become `Info`, `Warn` either `Error` or `Debug` depending on the message, `Crit` -> `Error`.
+
+This interface should go into `tmlibs/log`. All libraries which are part of the core (tendermint/tendermint) should obey it.
+
+### 2) Logger with our current formatting
+
+On top of this interface, we will need to implement a stdout logger, which will be used when Tendermint is configured to output logs to STDOUT.
+
+Many people say that they like the current output, so let's stick with it.
+
+```
+NOTE[04-25|14:45:08] ABCI Replay Blocks                       module=consensus appHeight=0 storeHeight=0 stateHeight=0
+```
+
+Couple of minor changes:
+
+```
+I[04-25|14:45:08.322] ABCI Replay Blocks            module=consensus appHeight=0 storeHeight=0 stateHeight=0
+```
+
+Notice the level is encoded using only one char plus milliseconds.
+
+Note: there are many other formats out there like [logfmt](https://brandur.org/logfmt).
+
+This logger could be implemented using any logger - [logrus](https://github.com/sirupsen/logrus), [go-kit/log](https://github.com/go-kit/kit/tree/master/log), [zap](https://github.com/uber-go/zap), log15 so far as it
+
+a) supports coloring output<br>
+b) is moderately fast (buffering) <br>
+c) conforms to the new interface or adapter could be written for it <br>
+d) is somewhat configurable<br>
+
+go-kit is my favorite so far. Check out how easy it is to color errors in red https://github.com/go-kit/kit/blob/master/log/term/example_test.go#L12. Although, coloring could only be applied to the whole string :(
+
+```
+go-kit +: flexible, modular
+go-kit “-”: logfmt format https://brandur.org/logfmt
+
+logrus +: popular, feature rich (hooks), API and output is more like what we want
+logrus -: not so flexible
+```
+
+```go
+# tm_logger.go
+// NewTmLogger returns a logger that encodes keyvals to the Writer in
+// tm format.
+func NewTmLogger(w io.Writer) Logger {
+  return &tmLogger{kitlog.NewLogfmtLogger(w)}
+}
+
+func (l tmLogger) SetLevel(level string() {
+  switch (level) {
+    case "debug":
+      l.sourceLogger = level.NewFilter(l.sourceLogger, level.AllowDebug())
+  }
+}
+
+func (l tmLogger) Info(msg string, keyvals ...interface{}) error {
+  l.sourceLogger.Log("msg", msg, keyvals...)
+}
+
+# log.go
+func With(logger Logger, keyvals ...interface{}) Logger {
+  kitlog.With(logger.sourceLogger, keyvals...)
+}
+```
+
+Usage:
+
+```go
+logger := log.NewTmLogger(os.Stdout)
+logger.SetLevel(config.GetString("log_level"))
+node.SetLogger(log.With(logger, "node", Name))
+```
+
+**Other log formatters**
+
+In the future, we may want other formatters like JSONFormatter.
+
+```
+{ "level": "notice", "time": "2017-04-25 14:45:08.562471297 -0400 EDT", "module": "consensus", "msg": "ABCI Replay Blocks", "appHeight": 0, "storeHeight": 0, "stateHeight": 0 }
+```
+
+### 3) Dynamic logger setting
+
+https://dave.cheney.net/2017/01/23/the-package-level-logger-anti-pattern
+
+This is the hardest part and where the most work will be done. logger should be tied to the processing struct, or the context if it adds some fields to the logger.
+
+```go
+type BaseService struct {
+    log     log15.Logger
+    name    string
+    started uint32 // atomic
+    stopped uint32 // atomic
+...
+}
+```
+
+BaseService already contains `log` field, so most of the structs embedding it should be fine. We should rename it to `logger`.
+
+The only thing missing is the ability to set logger:
+
+```
+func (bs *BaseService) SetLogger(l log.Logger) {
+  bs.logger = l
+}
+```
+
+### 4) Conventions
+
+Important keyvals should go first. Example:
+
+```
+correct
+I[04-25|14:45:08.322] ABCI Replay Blocks                       module=consensus instance=1 appHeight=0 storeHeight=0 stateHeight=0
+```
+
+not
+
+```
+wrong
+I[04-25|14:45:08.322] ABCI Replay Blocks                       module=consensus appHeight=0 storeHeight=0 stateHeight=0 instance=1
+```
+
+for that in most cases you'll need to add `instance` field to a logger upon creating, not when u log a particular message:
+
+```go
+colorFn := func(keyvals ...interface{}) term.FgBgColor {
+		for i := 1; i < len(keyvals); i += 2 {
+			if keyvals[i] == "instance" && keyvals[i+1] == "1" {
+				return term.FgBgColor{Fg: term.Blue}
+			} else if keyvals[i] == "instance" && keyvals[i+1] == "1" {
+				return term.FgBgColor{Fg: term.Red}
+			}
+		}
+		return term.FgBgColor{}
+	}
+logger := term.NewLogger(os.Stdout, log.NewTmLogger, colorFn)
+
+c1 := NewConsensusReactor(...)
+c1.SetLogger(log.With(logger, "instance", 1))
+
+c2 := NewConsensusReactor(...)
+c2.SetLogger(log.With(logger, "instance", 2))
+```
+
+## Status
+
+proposed
+
+## Consequences
+
+### Positive
+
+Dynamic logger, which could be turned off for some modules at runtime. Public interface for other projects using Tendermint libraries.
+
+### Negative
+
+We may loose the ability to color keys in keyvalue pairs. go-kit allow you to easily change foreground / background colors of the whole string, but not its parts.
+
+### Neutral
+
+## Appendix A.
+
+I really like a minimalistic approach go-kit took with his logger https://github.com/go-kit/kit/tree/master/log:
+
+```
+type Logger interface {
+    Log(keyvals ...interface{}) error
+}
+```
+
+See [The Hunt for a Logger Interface](https://go-talks.appspot.com/github.com/ChrisHines/talks/structured-logging/structured-logging.slide). The advantage is greater composability (check out how go-kit defines colored logging or log-leveled logging on top of this interface https://github.com/go-kit/kit/tree/master/log).

docs/architecture/adr-002-event-subscription.md

@@ -0,0 +1,90 @@
+# ADR 2: Event Subscription
+
+## Context
+
+In the light client (or any other client), the user may want to **subscribe to
+a subset of transactions** (rather than all of them) using `/subscribe?event=X`. For
+example, I want to subscribe for all transactions associated with a particular
+account. Same for fetching. The user may want to **fetch transactions based on
+some filter** (rather than fetching all the blocks). For example, I want to get
+all transactions for a particular account in the last two weeks (`tx's block
+time >= '2017-06-05'`).
+
+Now you can't even subscribe to "all txs" in Tendermint.
+
+The goal is a simple and easy to use API for doing that.
+
+![Tx Send Flow Diagram](img/tags1.png)
+
+## Decision
+
+ABCI app return tags with a `DeliverTx` response inside the `data` field (_for
+now, later we may create a separate field_). Tags is a list of key-value pairs,
+protobuf encoded.
+
+Example data:
+
+```json
+{
+  "abci.account.name": "Igor",
+  "abci.account.address": "0xdeadbeef",
+  "tx.gas": 7
+}
+```
+
+### Subscribing for transactions events
+
+If the user wants to receive only a subset of transactions, ABCI-app must
+return a list of tags with a `DeliverTx` response. These tags will be parsed and
+matched with the current queries (subscribers). If the query matches the tags,
+subscriber will get the transaction event.
+
+```
+/subscribe?query="tm.event = Tx AND tx.hash = AB0023433CF0334223212243BDD AND abci.account.invoice.number = 22"
+```
+
+A new package must be developed to replace the current `events` package. It
+will allow clients to subscribe to a different types of events in the future:
+
+```
+/subscribe?query="abci.account.invoice.number = 22"
+/subscribe?query="abci.account.invoice.owner CONTAINS Igor"
+```
+
+### Fetching transactions
+
+This is a bit tricky because a) we want to support a number of indexers, all of
+which have a different API b) we don't know whenever tags will be sufficient
+for the most apps (I guess we'll see).
+
+```
+/txs/search?query="tx.hash = AB0023433CF0334223212243BDD AND abci.account.owner CONTAINS Igor"
+/txs/search?query="abci.account.owner = Igor"
+```
+
+For historic queries we will need a indexing storage (Postgres, SQLite, ...).
+
+### Issues
+
+- https://github.com/tendermint/basecoin/issues/91
+- https://github.com/tendermint/tendermint/issues/376
+- https://github.com/tendermint/tendermint/issues/287
+- https://github.com/tendermint/tendermint/issues/525 (related)
+
+## Status
+
+proposed
+
+## Consequences
+
+### Positive
+
+- same format for event notifications and search APIs
+- powerful enough query
+
+### Negative
+
+- performance of the `match` function (where we have too many queries / subscribers)
+- there is an issue where there are too many txs in the DB
+
+### Neutral